© 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. 92859
    Prev
    Next
    INDEX
    Explanations

    technical identifiers

    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
     arrested
    -0.79
    rencia
    -0.76
    ilstein
    -0.74
    attled
    -0.71
     befür
    -0.70
     Swim
    -0.70
    meris
    -0.69
    V
    -0.68
    aldas
    -0.68
    퀴
    -0.68
    POSITIVE LOGITS
     Mousse
    0.78
    boven
    0.76
    磐
    0.74
     رژ
    0.72
     nanny
    0.69
    🐄
    0.65
     wharf
    0.65
    阉
    0.64
     sesión
    0.64
     Pacheco
    0.64
    Activations Density 0.058%

    No Known Activations