© 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. 78927
    Prev
    Next
    INDEX
    Explanations

    logo and brand imagery

    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
     Morten
    -0.71
    这点
    -0.71
    especial
    -0.69
    説
    -0.69
     influencia
    -0.69
    撳
    -0.68
    mesg
    -0.67
     Xs
    -0.67
    üyük
    -0.66
    bsen
    -0.66
    POSITIVE LOGITS
     logo
    5.72
    logo
    4.81
     Logo
    4.53
    Logo
    4.44
     logos
    4.38
    LOGO
    3.48
     LOGO
    3.42
    ロゴ
    2.97
     logotipo
    2.89
     Logos
    2.83
    Activations Density 0.070%

    No Known Activations