© 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. 191491
    Prev
    Next
    INDEX
    Explanations

    technical/scientific concepts and terms

    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
     کمپیو
    0.43
     manej
    0.42
    祁
    0.40
    akul
    0.39
    ikul
    0.39
    拟
    0.39
     évol
    0.39
    vänd
    0.39
    匡
    0.39
    فرض
    0.39
    POSITIVE LOGITS
    NUCLEAR
    0.37
     टेंशन
    0.37
     রি
    0.37
     parac
    0.36
     nuclear
    0.36
     intolerance
    0.36
    components
    0.35
    tension
    0.35
    Demi
    0.35
     components
    0.35
    Activations Density 0.001%

    No Known Activations