© 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. 34-GEMMASCOPE-RES-131K
    7. 92054
    Prev
    Next
    INDEX
    Explanations

    citation markers

    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
    htiö
    -0.73
     وف
    -0.72
    当た
    -0.69
    リリース
    -0.68
     Yoshida
    -0.68
     LOGIC
    -0.68
     SPIRIT
    -0.67
     Interpret
    -0.66
    BRIT
    -0.66
    Released
    -0.65
    POSITIVE LOGITS
    fdf
    0.71
    JEN
    0.66
    acab
    0.66
    🐼
    0.65
    դ
    0.64
    fí
    0.63
     tomo
    0.63
    vice
    0.63
    웨
    0.63
     ecco
    0.61
    Activations Density 0.052%

    No Known Activations