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. 22-GEMMASCOPE-2-RES-65K
    4. 3712
    Prev
    Next
    INDEX
    Explanations

    contrast, emphasis, and concluding punctuation

    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_22_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
    এছ
    0.78
    przy
    0.71
     również
    0.68
    适用于
    0.68
     همچنین
    0.68
    ֣
    0.66
     inoltre
    0.65
    又有
    0.65
    Gra
    0.64
    于
    0.62
    POSITIVE LOGITS
    .}
    1.36
    !.
    1.25
    !
    1.23
    !}
    1.20
    !”
    1.20
    .!
    1.17
     ;-)
    1.17
    .¹
    1.15
     :)
    1.15
    .},
    1.14
    Activations Density 0.075%

    No Known Activations