© 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. 79026
    Prev
    Next
    INDEX
    Explanations

    . batch its accordance exceptions services

    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
     or
    -0.84
     before
    -0.82
     Tôi
    -0.81
     basadas
    -0.79
     snippetHide
    -0.76
     cayó
    -0.76
     lưng
    -0.75
     liberación
    -0.75
    ของคุณ
    -0.75
    していると
    -0.74
    POSITIVE LOGITS
     termos
    0.86
    ₱
    0.86
     FRAMEWORK
    0.85
    zação
    0.84
     Journ
    0.84
     }}=
    0.83
     FOOT
    0.83
     Frid
    0.83
     amperes
    0.82
    менти
    0.81
    Activations Density 0.002%

    No Known Activations