© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 10953
    Prev
    Next
    INDEX
    Explanations

    phosphate compounds

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

    numeric data values in tables or structured data formats.

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

    The neuron activates on numeric tokens (particularly multi‐digit numbers) wherever they appear in the document.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     It
    -1.07
    镭
    -1.04
    For
    -1.04
     If
    -1.00
    laient
    -0.97
    kDa
    -0.94
    It
    -0.93
    Spec
    -0.90
    These
    -0.90
     При
    -0.88
    POSITIVE LOGITS
     Receives
    1.00
     понадоби
    1.00
     kopf
    0.94
    accom
    0.94
     Holistic
    0.94
    lieved
    0.91
     médicaments
    0.91
     commencer
    0.91
     critici
    0.91
     dessous
    0.91
    Activations Density 0.007%

    No Known Activations