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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25607
    Prev
    Next
    INDEX
    Explanations

    related art technical descriptions

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

    The neuron strongly fires on content-heavy nouns—especially technical or domain-specific terms—in formal or scientific text.

    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
     and
    -1.76
    ſt
    -1.09
     обратить
    -1.04
     и
    -1.03
     assorted
    -1.02
     начать
    -1.01
     verschieden
    -1.01
     betreffende
    -0.98
     kostenlosen
    -0.98
     lokalen
    -0.98
    POSITIVE LOGITS
     of
    1.46
     “
    1.20
     szüks
    1.19
     bisous
    1.16
     (
    1.10
    ÇÕES
    1.09
     bienvenue
    1.03
    磯
    1.03
     ſaid
    1.02
    ранее
    1.02
    Activations Density 0.073%

    No Known Activations