© 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. 148123
    Prev
    Next
    INDEX
    Explanations

    proposed rules

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

    socially rate Aut Gogh relatively

    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
    0.60
     accrue
    0.53
     beacons
    0.50
    sar
    0.50
     backlinks
    0.47
     declare
    0.45
     occurrence
    0.45
     =
    0.44
     outbursts
    0.44
     Republicans
    0.44
    POSITIVE LOGITS
    InstanceOf
    0.54
    していない
    0.54
    тила
    0.50
    тил
    0.49
    ointed
    0.49
    されていない
    0.48
    чены
    0.47
    を通じて
    0.46
    чему
    0.46
    শীল
    0.45
    Activations Density 0.000%

    No Known Activations