© 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. 47652
    Prev
    Next
    INDEX
    Explanations

    you need or will

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

    recent, biggest, free,Blocking

    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
    名的
    0.42
    이기
    0.42
    ⾼
    0.41
    徽
    0.39
    痊
    0.39
    듈
    0.38
    轮
    0.38
    螳
    0.38
    셀
    0.38
     ஆகியோர்
    0.38
    POSITIVE LOGITS
     saranam
    0.44
     t
    0.44
    ods
    0.42
    ua
    0.42
     कढ़ाई
    0.42
     paesi
    0.41
    od
    0.41
     letto
    0.41
     aves
    0.41
     shortlist
    0.41
    Activations Density 0.000%

    No Known Activations