© 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. 14568
    Prev
    Next
    INDEX
    Explanations

    standard input and output

    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
    g
    -2.16
    </b>
    -1.98
    st
    -1.78
    en
    -1.71
    r
    -1.52
    d
    -1.48
     allein
    -1.45
    4
    -1.41
     They
    -1.40
    day
    -1.39
    POSITIVE LOGITS
     capa
    1.76
    　↓
    1.63
    Ꮉ
    1.59
    一隻
    1.59
     pacote
    1.57
    購物
    1.54
    不可思议
    1.53
    脔
    1.53
    
    1.51
     ligeramente
    1.49
    Activations Density 0.028%

    No Known Activations