© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8615
    Prev
    Next
    INDEX
    Explanations

    data protection laws

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    美國
    0.57
     那麼
    0.55
     ベージュ
    0.54
     NASCAR
    0.52
    藝術
    0.52
     Cline
    0.52
     セ
    0.52
    သ
    0.51
     對
    0.51
    小說
    0.50
    POSITIVE LOGITS
     £
    0.55
     Anglia
    0.54
     GCSE
    0.54
     timescale
    0.51
     ब्रिटेन
    0.50
     британ
    0.50
     иң
    0.50
     Huddersfield
    0.50
     Cumbria
    0.49
    £
    0.49
    Activations Density 0.042%

    No Known Activations