© 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. 40-GEMMASCOPE-2-RES-262K
    7. 211672
    Prev
    Next
    INDEX
    Explanations

    AI image generation

    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_40_width_262k_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
     ஓடுப
    0.42
     neither
    0.40
    !(
    0.38
     mesi
    0.37
     Nasıl
    0.37
    👩
    0.37
     주어진
    0.37
     유형
    0.37
     Cómo
    0.36
     కాదు
    0.36
    POSITIVE LOGITS
    ゙
    0.44
    разде
    0.43
     Punkten
    0.42
    кар
    0.39
    ста
    0.39
    Fors
    0.39
     Fors
    0.39
     Including
    0.38
     honoured
    0.38
     mapDispatch
    0.37
    Activations Density 0.000%

    No Known Activations