© 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. 210082
    Prev
    Next
    INDEX
    Explanations

    consist of, impact on, Open Review

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

    ** prediction **

    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
    p
    0.58
    א
    0.48
    ্যান্ড
    0.47
    ].
    0.45
    ون
    0.45
    প
    0.43
    มัน
    0.42
    韩
    0.42
     didn
    0.41
    டெ
    0.41
    POSITIVE LOGITS
     autoestima
    0.52
    aii
    0.51
     rulemaking
    0.46
     એન
    0.45
    ulièrement
    0.44
     priorité
    0.44
     salari
    0.44
     Sí
    0.44
     reunited
    0.44
     leased
    0.43
    Activations Density 0.000%

    No Known Activations