© 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. 158783
    Prev
    Next
    INDEX
    Explanations

    ordering, harvesting, foraging, art, hunger

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

    vibe check 💀

    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
    πό
    0.50
     آپ
    0.46
    い
    0.46
    り
    0.44
    蔷
    0.44
    炮
    0.44
    σή
    0.44
    闱
    0.44
     }^{-
    0.43
     αγο
    0.43
    POSITIVE LOGITS
     foraging
    0.52
    database
    0.49
     goalie
    0.46
     TOOLS
    0.46
     scouting
    0.45
     Harvesting
    0.44
    ಕೊ
    0.44
    visualization
    0.44
    mechan
    0.44
     Wildlife
    0.43
    Activations Density 0.000%

    No Known Activations