© 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. 144722
    Prev
    Next
    INDEX
    Explanations

    rescue progress bill

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

    potential dependencies, roadblocks

    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
    െ
    0.44
    AddNew
    0.44
    ,/*
    0.43
    Notice
    0.43
    فة
    0.43
    ي
    0.42
    th
    0.41
    جة
    0.41
    暌
    0.41
    ను
    0.41
    POSITIVE LOGITS
     tuoi
    0.48
     flapping
    0.48
     brukes
    0.47
     pivots
    0.46
    เภท
    0.45
    ვენ
    0.45
    łączyć
    0.45
     instabilities
    0.44
     divent
    0.44
     agricoles
    0.44
    Activations Density 0.001%

    No Known Activations