© 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. 169183
    Prev
    Next
    INDEX
    Explanations

    RPC tracing, immortalize, cool, high skilled

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

    larger in scope or size

    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
     gratuitos
    0.49
     limitée
    0.46
    مكان
    0.45
     gratuitamente
    0.45
     kotak
    0.45
    ْع
    0.45
     caixa
    0.45
     colocadas
    0.44
    άν
    0.43
     affords
    0.43
    POSITIVE LOGITS
    针对
    0.46
     देखते
    0.43
    ‐
    0.42
    ગાહી
    0.42
    话题
    0.41
    acak
    0.41
     دیکھتے
    0.40
    颖
    0.40
    本科
    0.39
     வடி
    0.39
    Activations Density 0.000%

    No Known Activations