© 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. 39515
    Prev
    Next
    INDEX
    Explanations

    prognostic factors and fresh ideas

    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_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
    '
    -2.50
     adorned
    -2.03
    -
    -2.02
     ‘
    -1.99
     —
    -1.95
    を使用した
    -1.85
     durante
    -1.82
    を使う
    -1.71
    を使
    -1.70
    
    -1.69
    POSITIVE LOGITS
    These
    2.28
    Also
    2.22
    This
    2.14
     Also
    2.03
     sebagainya
    1.94
    🫶
    1.88
    تیب
    1.84
    Some
    1.81
     for
    1.78
    Those
    1.77
    Activations Density 0.031%

    No Known Activations