© 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. 10-GEMMASCOPE-RES-131K
    7. 100878
    Prev
    Next
    INDEX
    Explanations

    digit 4

    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
     develops
    -1.96
    絎
    -1.94
    ⢇
    -1.94
     induces
    -1.92
    ＂
    -1.91
    咴
    -1.89
     indústria
    -1.86
     increases
    -1.85
     énfasis
    -1.85
    銪
    -1.84
    POSITIVE LOGITS
    >
    2.14
    0
    2.08
    —
    1.99
    说
    1.96
    abinieri
    1.86
    al
    1.84
    进攻
    1.84
     Monaten
    1.77
     he
    1.77
    模样
    1.76
    Activations Density 0.028%

    No Known Activations