© 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. 34-GEMMASCOPE-RES-131K
    7. 63963
    Prev
    Next
    INDEX
    Explanations

    numbers 0-9 and punctuation

    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
     Need
    -0.93
     Will
    -0.88
     need
    -0.87
    Need
    -0.86
     Should
    -0.81
     corresponding
    -0.78
    łom
    -0.78
     cuando
    -0.76
    <mask>
    -0.75
    Will
    -0.75
    POSITIVE LOGITS
    nini
    0.99
    lossal
    0.90
    ברית
    0.90
     digger
    0.89
     FTA
    0.89
    vestres
    0.88
    trecht
    0.88
    mai
    0.85
     *((
    0.84
     MAI
    0.83
    Activations Density 0.033%

    No Known Activations