© 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. 40-GEMMASCOPE-2-RES-262K
    7. 5964
    Prev
    Next
    INDEX
    Explanations

    character types and ranges

    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_40_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
    <bbox>
    0.44
    getRedTeam
    0.43
    膝
    0.42
     खरेदी
    0.42
    COMANDA
    0.42
    AHN
    0.41
    बंधनाच्या
    0.41
    朋友圈
    0.41
    鲸
    0.41
    찜
    0.40
    POSITIVE LOGITS
     characters
    1.74
     letters
    1.74
    字符
    1.68
     Characters
    1.62
    字母
    1.59
    characters
    1.59
     Buchstaben
    1.56
     letter
    1.55
     Letters
    1.55
    Characters
    1.54
    Activations Density 0.141%

    No Known Activations