© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64954
    Prev
    Next
    INDEX
    Explanations

    Frank Effects, SHINE detector, Brookhaven National Laboratory, LIP

    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
    őtt
    -0.73
     using
    -0.71
     dazzling
    -0.68
     weren
    -0.68
     areas
    -0.67
     test
    -0.66
     Hej
    -0.66
     śpiew
    -0.65
     What
    -0.65
     daba
    -0.65
    POSITIVE LOGITS
     ALICE
    1.28
     INVEST
    0.90
     connecté
    0.89
     alice
    0.88
    Vz
    0.85
    প্র
    0.85
    Projectile
    0.81
     SHAPE
    0.81
    чены
    0.79
     zaj
    0.78
    Activations Density 0.024%

    No Known Activations