© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115662
    Prev
    Next
    INDEX
    Explanations

    Solute carrier family 22

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and numeric patterns in technical and scientific text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron activates on numeric version strings—sequences of digits and dots (e.g. “2.0,” “1.3.6.1…”) in technical or XML-like contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     during
    -1.34
     on
    -1.30
     by
    -1.22
     through
    -1.18
     while
    -1.15
     in
    -1.14
     with
    -1.10
     gives
    -1.10
     from
    -1.07
     being
    -1.05
    POSITIVE LOGITS
     vii
    1.06
     pivotal
    1.04
    potentially
    1.03
    וך
    1.03
    atii
    1.02
     horrid
    1.01
     sooo
    1.00
     castig
    0.99
     ornate
    0.97
     dilapidated
    0.97
    Activations Density 0.000%

    No Known Activations