© 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. 154860
    Prev
    Next
    INDEX
    Explanations

    installing or buying

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

    words or list

    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
    於
    0.49
    攻略
    0.49
    僥
    0.48
    在他的
    0.47
    徬
    0.46
    回顾
    0.44
    }$;
    0.43
    曾經
    0.42
    慰
    0.42
    的角色
    0.41
    POSITIVE LOGITS
     Natur
    0.48
     natura
    0.48
     Aliment
    0.46
     with
    0.46
     eso
    0.46
     file
    0.45
     enzymatic
    0.45
     ignited
    0.45
    pFile
    0.44
     that
    0.44
    Activations Density 0.000%

    No Known Activations