© 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. 2869
    Prev
    Next
    INDEX
    Explanations

    document provider

    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
    AME
    -0.77
    ު
    -0.73
    ruptedException
    -0.73
    癢
    -0.71
    andar
    -0.71
    insk
    -0.69
     mauvaises
    -0.69
    hejiang
    -0.69
    ophe
    -0.69
     slats
    -0.69
    POSITIVE LOGITS
     my
    1.73
     f
    1.34
    my
    1.14
     its
    1.08
     мой
    1.01
     our
    0.96
     мои
    0.92
    f
    0.90
     mijn
    0.85
     their
    0.82
    Activations Density 0.044%

    No Known Activations