© 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-65K
    7. 28062
    Prev
    Next
    INDEX
    Explanations

    lists of items ending with commas

    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_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
     المبار
    0.37
    粤
    0.36
    μά
    0.35
    ি
    0.35
    читать
    0.34
    묘
    0.34
    哺乳
    0.33
    ի
    0.33
     કહ્યું
    0.33
    ী
    0.33
    POSITIVE LOGITS
    ،
    0.45
     તેમજ
    0.44
     %,
    0.43
    、
    0.43
    ,
    0.43
    ，
    0.43
     ,
    0.42
     ፣
    0.42
    (),
    0.40
    %,
    0.39
    Activations Density 0.052%

    No Known Activations