© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-65K
    4. 383
    Prev
    Next
    INDEX
    Explanations

    analogies and examples

    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_16_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
     
    0.45
    on
    0.45
    颢
    0.44
    ↵↵
    0.44
    }
    0.42
    ٣
    0.42
    ()}
    0.41
    ны
    0.41
    (
    0.41
     ={
    0.40
    POSITIVE LOGITS
    ہ
    0.66
     or
    0.57
    %
    0.56
     and
    0.54
     but
    0.52
     unethical
    0.51
     spoiling
    0.45
     in
    0.45
     detriment
    0.44
     compliqué
    0.43
    Activations Density 0.001%

    No Known Activations