© 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. 191464
    Prev
    Next
    INDEX
    Explanations

    various contexts and consequences

    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
     savages
    0.45
     savage
    0.43
     hypogly
    0.40
     formulae
    0.39
     vicious
    0.38
    생
    0.37
     annih
    0.37
    Coref
    0.37
     fórmulas
    0.36
    ībā
    0.36
    POSITIVE LOGITS
    dio
    0.38
     “
    0.38
    0.37
    น์โหลด
    0.37
     readiness
    0.37
     weekly
    0.36
     Readiness
    0.36
    ̉
    0.36
    🏪
    0.36
     দিয়েছেন
    0.35
    Activations Density 0.000%

    No Known Activations