© 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. 10-GEMMASCOPE-RES-131K
    7. 8412
    Prev
    Next
    INDEX
    Explanations

    programming interfaces

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

    This neuron detects occurrences of the identifier “Interface” (e.g. in code declarations and import statements).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ’,
    -2.70
     Geschäfte
    -2.38
     Our
    -2.19
    来て
    -2.17
    ’;
    -2.11
     weshalb
    -2.02
     большим
    -2.00
    イケ
    -2.00
     ‘
    -1.97
     Your
    -1.95
    POSITIVE LOGITS
    猹
    3.02
    瘓
    2.59
    .
    2.58
     desee
    2.56
     continúas
    2.53
     retira
    2.44
    齣
    2.44
     cubano
    2.41
     chileno
    2.39
    ⬐
    2.36
    Activations Density 0.010%

    No Known Activations