© 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. 63749
    Prev
    Next
    INDEX
    Explanations

    ServiceStack namespaces

    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
    wag
    -0.69
     incompatible
    -0.68
     системе
    -0.67
    nip
    -0.65
     Domin
    -0.65
     prosty
    -0.64
    hausen
    -0.64
    cheduler
    -0.63
    IDENTIFIER
    -0.63
    ⫻
    -0.63
    POSITIVE LOGITS
     服务
    0.68
    Azul
    0.68
     DBMS
    0.66
     transitioning
    0.66
     स्त
    0.65
     縣
    0.65
    Interes
    0.64
    Jahre
    0.63
    entlig
    0.63
    Hoa
    0.63
    Activations Density 0.108%

    No Known Activations