© 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. 30777
    Prev
    Next
    INDEX
    Explanations

    Indian followed by an entity

    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
    HXLINE
    -0.83
     оку
    -0.79
    ථ
    -0.76
    ꪮ
    -0.76
     wyra
    -0.76
    攝影
    -0.75
    DOB
    -0.73
    🦼
    -0.73
     徐
    -0.73
    accumulative
    -0.72
    POSITIVE LOGITS
    tshire
    0.84
    sizes
    0.79
     على
    0.77
     empresa
    0.72
     jedoch
    0.72
     getNome
    0.71
     rosse
    0.71
    µ
    0.71
    haft
    0.71
    覺
    0.71
    Activations Density 0.020%

    No Known Activations