© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200455
    Prev
    Next
    INDEX
    Explanations

    no character names mentioned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     questionnaires
    0.56
    ant
    0.49
     examinations
    0.47
     look
    0.47
     surrog
    0.46
    ח
    0.43
    ونی
    0.43
     oppress
    0.43
     surveillance
    0.43
    ת
    0.43
    POSITIVE LOGITS
    *}\
    0.50
    出版
    0.46
    ﻻ
    0.45
     গ্রাহ
    0.42
    制造商
    0.42
    ɗ
    0.42
     Modelo
    0.41
     សូម
    0.41
     FontFamily
    0.41
    朗普
    0.41
    Activations Density 0.002%

    No Known Activations