Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 1138
    Prev
    Next
    INDEX
    Explanations

    words followed by commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
     ਸੀ
    0.72
     harboring
    0.63
     Shazam
    0.59
     visibly
    0.59
     thrilled
    0.57
    ダス
    0.57
    ñones
    0.57
     උ
    0.57
    堇
    0.57
     Deluxe
    0.57
    POSITIVE LOGITS
    ,
    1.16
    、
    0.99
    ,/
    0.90
    ,-
    0.84
    ،
    0.84
    -,
    0.83
    ፣
    0.80
    ,_
    0.80
    、
    0.79
    ,\
    0.78
    Activations Density 0.844%

    No Known Activations