© 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. 40-GEMMASCOPE-2-RES-262K
    4. 120118
    Prev
    Next
    INDEX
    Explanations

    AI Now, Beginner Level

    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
     इंडोनेशिया
    0.41
     खरीदी
    0.40
     Nói
    0.40
    ആ
    0.40
    readValue
    0.39
     रेसिपी
    0.39
    문제
    0.38
     Украины
    0.38
    蕉
    0.38
     मलेशिया
    0.38
    POSITIVE LOGITS
     etiquetas
    0.38
     coercive
    0.37
     unarmed
    0.36
     respir
    0.36
    젠
    0.36
    থম
    0.35
    services
    0.35
     services
    0.35
    já
    0.35
     চক্ষে
    0.35
    Activations Density 0.011%

    No Known Activations