© 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. 52459
    Prev
    Next
    INDEX
    Explanations

    important to or for

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

    essential to

    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
     remarkable
    0.39
     フラワー
    0.39
     जुगा
    0.38
    remarkable
    0.38
    ಶ್ರೀ
    0.38
    寺
    0.37
     Tumblr
    0.37
    žas
    0.37
     websocket
    0.37
     ओली
    0.37
    POSITIVE LOGITS
    ที่จะ
    0.52
     to
    0.46
    itized
    0.46
    levard
    0.43
    мин
    0.42
    Ov
    0.41
     downtown
    0.41
    কেশ
    0.41
    Ꮏ
    0.40
    Woods
    0.40
    Activations Density 0.001%

    No Known Activations