© 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. 120250
    Prev
    Next
    INDEX
    Explanations

    Day of action, Theta, injury, rally, causal chain

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

    generation or writing placeholders

    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
     ジャ
    0.50
     लीजिएगा
    0.49
     ছেলেদের
    0.49
    с
    0.49
     えっ
    0.47
     Jand
    0.47
     Neub
    0.46
     Marcel
    0.45
     Newton
    0.44
    বলে
    0.44
    POSITIVE LOGITS
    Etudes
    0.53
    嗉
    0.53
    首先
    0.52
    秘书
    0.51
    瘧
    0.51
    匏
    0.51
     that
    0.50
    특히
    0.50
     applique
    0.47
    是
    0.47
    Activations Density 0.000%

    No Known Activations