© 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. 106801
    Prev
    Next
    INDEX
    Explanations

    software licenses and debugging

    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
    nv
    -0.72
     kiedyś
    -0.71
     привет
    -0.71
    irt
    -0.71
     Achievements
    -0.68
     Iterate
    -0.68
     cuddly
    -0.66
    ऍ
    -0.65
    enne
    -0.65
     Ephe
    -0.64
    POSITIVE LOGITS
    mno
    0.81
    Wait
    0.81
     Cosmetics
    0.80
    выя
    0.80
     toi
    0.79
    melons
    0.79
     fran
    0.78
     liker
    0.77
     Frankfurter
    0.77
    colazione
    0.77
    Activations Density 0.001%

    No Known Activations