© 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. 22-GEMMASCOPE-RES-131K
    7. 64900
    Prev
    Next
    INDEX
    Explanations

    code block start

    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
    Così
    -1.00
    ÁND
    -0.98
     zwi
    -0.95
     Questo
    -0.94
    proken
    -0.93
     Berechnung
    -0.92
    зії
    -0.92
     Krzysz
    -0.91
    Siamo
    -0.89
     Uniwers
    -0.88
    POSITIVE LOGITS
     silueta
    0.99
     is
    0.99
    亮点
    0.98
     its
    0.95
    各项
    0.94
     understand
    0.93
    рити
    0.91
     pausa
    0.90
     well
    0.90
    作为一个
    0.90
    Activations Density 0.014%

    No Known Activations