© 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. 72964
    Prev
    Next
    INDEX
    Explanations

    signed, new, or follicular

    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
     they
    -1.25
     zobaczyć
    -1.20
     zrobić
    -1.20
     kupić
    -1.15
     "")
    -1.11
    ktör
    -1.10
    ोजना
    -1.10
    atase
    -1.09
     into
    -1.06
     operación
    -1.06
    POSITIVE LOGITS
     two
    1.27
     Two
    1.16
     Australian
    1.07
    ACGIH
    1.03
     Italian
    1.02
     TWO
    1.02
    Two
    1.01
     الفترة
    0.99
    Ivo
    0.98
     Nomination
    0.98
    Activations Density 0.146%

    No Known Activations