© 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. 15470
    Prev
    Next
    INDEX
    Explanations

    import from

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

    The neuron fires on the “from” keyword (and “require” call) that introduces a module path in import or require 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_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
    aziland
    -1.25
    ец
    -1.06
    4
    -1.03
    лото
    -1.00
    5
    -0.97
    7
    -0.96
    8
    -0.94
    acka
    -0.94
    toPromise
    -0.93
    доры
    -0.93
    POSITIVE LOGITS
     are
    1.17
    respectively
    1.16
     arasındaki
    1.03
    それぞれ
    1.02
     jeweils
    1.01
    områ
    0.98
     Siehe
    0.97
    倌
    0.94
     zonder
    0.93
    yesha
    0.92
    Activations Density 0.004%

    No Known Activations