© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8030
    Prev
    Next
    INDEX
    Explanations

    internet domain names

    np_acts-logits-general · gemini-2.5-flash-lite

    .org/ URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ='+
    0.48
    '=>
    0.43
    Kabhi
    0.41
    legant
    0.41
    ':[
    0.41
    ội
    0.41
    によっては
    0.41
    Which
    0.40
     Which
    0.40
     `=
    0.40
    POSITIVE LOGITS
    /),
    0.54
    ‘
    0.49
    facebook
    0.48
    subscribe
    0.46
    about
    0.46
    /?
    0.44
     Facebook
    0.44
    ‎
    0.44
    /#
    0.43
     facebook
    0.43
    Activations Density 0.038%

    No Known Activations