© 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. 2417
    Prev
    Next
    INDEX
    Explanations

    dappled, Dakota Johnson, Dahl, DALL-E

    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
     Nähe
    0.42
     ಸಾಕ
    0.41
     Öffentlichkeit
    0.40
    地形
    0.40
     Sozial
    0.38
    ṱ
    0.38
    Ꮘ
    0.38
     فلا
    0.38
    ёд
    0.37
    ).\
    0.37
    POSITIVE LOGITS
     DA
    0.65
    DA
    0.55
     DAP
    0.54
     Da
    0.52
     ダ
    0.51
     Daf
    0.51
     DAI
    0.50
     DAC
    0.48
     Dah
    0.47
     Dau
    0.47
    Activations Density 0.023%

    No Known Activations