© 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. 242002
    Prev
    Next
    INDEX
    Explanations

    pothos

    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
     отра
    0.48
    রাষ্ট্র
    0.43
     раздела
    0.42
    🧹
    0.42
     docket
    0.41
    п
    0.41
     sacrament
    0.41
    Ყ
    0.41
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.40
     pastry
    0.40
    POSITIVE LOGITS
    eg
    0.48
    avourites
    0.46
     කළ
    0.45
     BLUEN
    0.44
     درب
    0.43
    edinte
    0.43
     risc
    0.42
    guide
    0.42
    ezing
    0.42
    jut
    0.41
    Activations Density 0.003%

    No Known Activations