© 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. 36092
    Prev
    Next
    INDEX
    Explanations

    roles and people

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

    The neuron detects code identifiers—particularly database table and column names (e.g. Tecnico, medic, Manager_ID).

    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
     some
    -1.28
    revet
    -1.13
     Some
    -1.08
     it
    -1.08
    styrelsen
    -1.04
    getTimestamp
    -1.04
     jurí
    -1.03
    ország
    -1.03
     this
    -0.98
    env
    -0.98
    POSITIVE LOGITS
     who
    1.95
     whom
    1.40
     îna
    1.19
     profile
    1.17
     talents
    1.13
    情報は
    1.13
    ígen
    1.11
     biography
    1.05
     przód
    1.05
     salary
    1.03
    Activations Density 0.017%

    No Known Activations