© 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. 108011
    Prev
    Next
    INDEX
    Explanations

    Choque-Rei

    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
     Byz
    -0.85
     toga
    -0.85
     universities
    -0.85
    ínica
    -0.82
     corporativa
    -0.79
     strass
    -0.78
     POSTS
    -0.77
     sovi
    -0.77
    ovatel
    -0.76
     Soundtrack
    -0.76
    POSITIVE LOGITS
    xodo
    0.88
    ombre
    0.83
     Clock
    0.79
    dick
    0.77
    clock
    0.77
     Sikh
    0.76
    Radians
    0.76
     VOC
    0.76
     Company
    0.75
    ndl
    0.75
    Activations Density 0.049%

    No Known Activations