© 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. 51932
    Prev
    Next
    INDEX
    Explanations

    implementation of new technologies

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

    running instances, strike price, feelings

    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
    厉害
    0.55
    內的
    0.50
     үнд
    0.48
     ध्वस्त
    0.47
    መሳ
    0.46
    률
    0.46
    ToIndex
    0.45
    sächlich
    0.44
    癌症
    0.44
    跆
    0.44
    POSITIVE LOGITS
     Manu
    0.45
     shark
    0.44
     Zhou
    0.44
     heterozygous
    0.44
     Shark
    0.43
     Sharks
    0.43
    やや
    0.43
     unsure
    0.42
     shrimps
    0.42
     logistics
    0.41
    Activations Density 0.000%

    No Known Activations