© 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. 15670
    Prev
    Next
    INDEX
    Explanations

    only or never

    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
     impactful
    0.45
    ก็
    0.45
     badass
    0.44
     poignant
    0.43
     kiddos
    0.43
     כש
    0.42
     ก็
    0.42
     '[
    0.42
     även
    0.42
     evocative
    0.42
    POSITIVE LOGITS
     wyłącznie
    0.73
     exclusively
    0.58
     केवल
    0.56
     only
    0.56
    only
    0.54
     únicamente
    0.54
     solamente
    0.54
     uniquement
    0.53
     반드시
    0.52
     কখনোই
    0.52
    Activations Density 0.058%

    No Known Activations