© 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. 22-GEMMASCOPE-RES-131K
    7. 14427
    Prev
    Next
    INDEX
    Explanations

    legal and official documents

    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_22/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
     in
    -0.99
    umfang
    -0.89
     at
    -0.88
     unparalleled
    -0.85
     supremely
    -0.81
    MEC
    -0.81
     ultima
    -0.79
     for
    -0.79
     Geraadpleegd
    -0.78
     motivasi
    -0.78
    POSITIVE LOGITS
    alaya
    1.03
    quiti
    0.93
     poursuivre
    0.89
    containing
    0.85
    established
    0.85
    hithe
    0.85
     delightful
    0.85
     dismal
    0.84
    itul
    0.84
     luscious
    0.84
    Activations Density 0.006%

    No Known Activations