© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 26251
    Prev
    Next
    INDEX
    Explanations

    Al Davis

    np_acts-logits-general · gemini-2.5-flash-lite

    apply and interpret data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     watery
    0.49
     tasty
    0.48
    л
    0.46
     curvy
    0.45
     soapy
    0.45
     steaming
    0.44
     regione
    0.43
    д
    0.43
    vollen
    0.42
    pairwise
    0.42
    POSITIVE LOGITS
    請問
    0.45
    ហារ
    0.42
    还是要
    0.41
    实在是
    0.41
     bukanlah
    0.40
     सुद्धा
    0.40
     Gleason
    0.40
    變
    0.40
    ické
    0.39
    年モデル
    0.39
    Activations Density 0.000%

    No Known Activations