© 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. 202116
    Prev
    Next
    INDEX
    Explanations

    synthetic sapphires

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

    software readily available

    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
    萝卜
    0.47
    呈现
    0.46
    谜
    0.43
    大哥
    0.43
    爸爸
    0.43
    荪
    0.42
    汉
    0.42
    Bonus
    0.42
    뽀
    0.41
    Blend
    0.41
    POSITIVE LOGITS
     commemorated
    0.57
    öyle
    0.50
    twenty
    0.50
     twenty
    0.48
    countries
    0.47
    had
    0.46
    язви
    0.46
    iteits
    0.46
    㥳
    0.46
    states
    0.46
    Activations Density 0.001%

    No Known Activations