© 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. 10-GEMMASCOPE-RES-131K
    7. 129015
    Prev
    Next
    INDEX
    Explanations

    NES, Agora, NSS, MvxBind

    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_10/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
     Möglich
    -2.63
     This
    -2.56
    inée
    -2.55
     uczniów
    -2.34
    CurtirCurtir
    -2.31
     Beobachtungen
    -2.31
    珖
    -2.30
    倻
    -2.28
    
    -2.28
    ugais
    -2.27
    POSITIVE LOGITS
    Y
    3.48
    er
    3.44
    b
    3.25
    J
    3.22
    e
    3.20
    M
    3.09
    K
    3.06
    X
    3.06
    t
    3.05
    or
    2.92
    Activations Density 0.046%

    No Known Activations