© 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. 200840
    Prev
    Next
    INDEX
    Explanations

    custom-made ocular prosthesis

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

    totally dramatic

    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
    を使って
    0.46
    cuterie
    0.46
    具合
    0.44
    kannya
    0.43
    უშა
    0.43
    県
    0.42
    ри
    0.42
    やる
    0.42
    ايا
    0.42
    鐢
    0.42
    POSITIVE LOGITS
     outcrop
    0.49
     imperio
    0.48
     paramet
    0.46
     concreto
    0.46
     aq
    0.45
     elemento
    0.44
     impar
    0.44
     μπο
    0.44
     edibles
    0.44
     aquello
    0.43
    Activations Density 0.001%

    No Known Activations