© 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. 78260
    Prev
    Next
    INDEX
    Explanations

    prefixes followed by words

    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
    を
    -1.11
    と
    -1.08
     in
    -0.98
    to
    -0.97
    vasive
    -0.95
    g
    -0.93
     after
    -0.93
     unrelenting
    -0.89
    ympto
    -0.89
    に
    -0.88
    POSITIVE LOGITS
     nadru
    1.13
     Dinas
    1.05
    reached
    1.03
    を変更
    1.00
     Ін
    1.00
    breathe
    0.99
     zoude
    0.99
    РС
    0.99
     Ini
    0.98
    ENIE
    0.98
    Activations Density 0.096%

    No Known Activations