© 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. 144979
    Prev
    Next
    INDEX
    Explanations

    sell or fail

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

    English text structure

    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
    ۳
    0.47
    修改
    0.44
    時間に
    0.43
    热
    0.43
    真实的
    0.42
    avanja
    0.42
    해보
    0.42
    𝙴
    0.40
    新たな
    0.40
    getattr
    0.40
    POSITIVE LOGITS
    ፣
    0.53
    ،
    0.52
     hinder
    0.51
     organisme
    0.50
     hind
    0.49
     neurologic
    0.47
     риск
    0.47
     render
    0.46
     beteg
    0.45
    ปรา
    0.45
    Activations Density 0.000%

    No Known Activations