© 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. 86118
    Prev
    Next
    INDEX
    Explanations

    directions and names

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

    affirmations, resistance, fix, competing

    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
    𝙜
    0.56
    𝗴
    0.55
    繖
    0.52
     uży
    0.50
     {}>,
    0.50
     pathMatch
    0.49
    сант
    0.49
    [,,"
    0.49
    𝘻
    0.49
    欉
    0.49
    POSITIVE LOGITS
     heroine
    0.49
     divorced
    0.49
     historie
    0.47
    Ross
    0.46
     Ross
    0.46
     vicious
    0.46
     nurse
    0.44
    are
    0.44
     are
    0.43
     positive
    0.43
    Activations Density 0.000%

    No Known Activations