© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3429
    Prev
    Next
    INDEX
    Explanations

    past, improve, core, transmission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    承包人
    1.46
    ovich
    1.35
    顱
    1.35
     bimodule
    1.32
    odule
    1.32
    cinas
    1.31
     "'";
    1.28
    一層
    1.28
    濤
    1.28
     '';
    1.27
    POSITIVE LOGITS
    熹
    1.01
     wipes
    1.01
    Zy
    0.96
    Sweep
    0.94
    映
    0.92
    VAS
    0.92
    Pip
    0.92
     searched
    0.92
    拜
    0.91
     prophecies
    0.90
    Activations Density 0.019%

    No Known Activations