© 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. 127863
    Prev
    Next
    INDEX
    Explanations

    before ship

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

    python code

    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
     Principles
    0.50
     Press
    0.48
     principles
    0.48
    夗
    0.48
     Operations
    0.45
     environmental
    0.45
     বঙ্গবন্ধুর
    0.45
     Young
    0.45
     Day
    0.44
     projectiles
    0.43
    POSITIVE LOGITS
    Exist
    0.47
    aih
    0.47
    を受け
    0.45
    닿
    0.44
    lamydia
    0.43
    inafter
    0.42
    เคราะห์
    0.42
    razia
    0.42
    けると
    0.41
     الخامسه
    0.41
    Activations Density 0.000%

    No Known Activations