© 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. 2783
    Prev
    Next
    INDEX
    Explanations

    punctuation and specific endings

    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
    mapa
    -0.74
     пад
    -0.69
    لسلة
    -0.69
    romptu
    -0.68
    лябин
    -0.68
     Application
    -0.66
     Він
    -0.66
     LY
    -0.65
    acan
    -0.65
    ટે
    -0.65
    POSITIVE LOGITS
    erna
    0.92
    kowski
    0.91
    SignUp
    0.88
    STARS
    0.83
     Paroles
    0.81
    ！」
    0.81
    传来
    0.80
    ୨
    0.80
    ботинки
    0.79
     dég
    0.79
    Activations Density 0.001%

    No Known Activations