© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91790
    Prev
    Next
    INDEX
    Explanations

    articles before 'basis' context

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

    The neuron strongly activates on the licensing‐disclaimer phrase “on an ‘AS IS’ BASIS,” as used in Apache‐style copyright headers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     ekolog
    -0.87
     nyeri
    -0.84
     jugend
    -0.79
    Laughs
    -0.75
     på
    -0.75
     Wade
    -0.74
    ویژگی
    -0.74
    based
    -0.73
     operation
    -0.73
    ionar
    -0.73
    POSITIVE LOGITS
    cionario
    0.84
     as
    0.80
    @\
    0.79
     quæ
    0.78
    鄂
    0.77
    casse
    0.77
     sliding
    0.77
     soles
    0.76
    _/
    0.76
     Greenfield
    0.76
    Activations Density 0.053%

    No Known Activations