© 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. 63895
    Prev
    Next
    INDEX
    Explanations

    Q or announcement

    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
     suitable
    -0.84
     before
    -0.79
     good
    -0.79
     unofficial
    -0.73
     useful
    -0.73
     several
    -0.73
     you
    -0.71
     needless
    -0.71
     ideal
    -0.71
    必ず
    -0.71
    POSITIVE LOGITS
    <>
    1.04
     <>
    1.00
    λίου
    0.90
    бл
    0.90
    átu
    0.89
     године
    0.88
    이의
    0.85
    煜
    0.84
    nante
    0.83
    ={<
    0.82
    Activations Density 0.001%

    No Known Activations