© 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. 188287
    Prev
    Next
    INDEX
    Explanations

    apparently planted

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

    good leader, easily visualized

    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
    Fire
    0.43
    да
    0.42
    ((
    0.42
     Spear
    0.41
    Drive
    0.41
    Voice
    0.41
    Subscribe
    0.41
    “”
    0.40
    펀
    0.40
    POSITIVE LOGITS
     toilette
    0.52
     vêtements
    0.49
     mať
    0.49
    ന്തര
    0.48
     teníamos
    0.47
    フルーツ
    0.46
    nissen
    0.46
     حسین
    0.45
    uities
    0.45
     vidéo
    0.45
    Activations Density 0.001%

    No Known Activations