© 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. 34-GEMMASCOPE-RES-131K
    7. 89980
    Prev
    Next
    INDEX
    Explanations

    mathematical structure and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     dirección
    -0.82
     especially
    -0.78
     zau
    -0.76
    IAS
    -0.75
     особли
    -0.71
     a
    -0.70
    (+)
    -0.69
    ULI
    -0.68
     אלא
    -0.68
    を見
    -0.68
    POSITIVE LOGITS
    のではないか
    1.05
     palab
    0.85
    際には
    0.82
    色々と
    0.82
    ようですが
    0.82
    為に
    0.82
     coklat
    0.82
    必要があります
    0.81
    ことも
    0.81
    Trois
    0.81
    Activations Density 0.052%

    No Known Activations