© 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. 2858
    Prev
    Next
    INDEX
    Explanations

    replace or install parts

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

    replacement parts and accessories

    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
    政治
    0.71
     राजनीतिक
    0.69
    राजनी
    0.69
    社會
    0.69
     полити
    0.68
     اجتماعی
    0.66
     politič
    0.66
    <unused29>
    0.64
     político
    0.64
     політи
    0.63
    POSITIVE LOGITS
     replacement
    1.29
     replacements
    1.22
     Replacement
    1.09
     replacing
    1.06
     replace
    1.05
    替换
    1.05
     installed
    1.02
    replacement
    1.02
     replaced
    0.96
     replaces
    0.96
    Activations Density 0.362%

    No Known Activations