© 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. 84361
    Prev
    Next
    INDEX
    Explanations

    in Britain prior step

    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
    ..--
    0.41
    dosage
    0.39
    嘩
    0.38
     "-//
    0.38
    ኩ
    0.37
    Specification
    0.36
     ছুরি
    0.36
     کہنا
    0.35
    컴
    0.35
    Bomb
    0.34
    POSITIVE LOGITS
     Alem
    0.47
     sign
    0.41
     chars
    0.40
     sant
    0.40
     mith
    0.40
    ्यूशन
    0.40
     chariot
    0.40
     SIGN
    0.40
     teor
    0.39
     youtube
    0.39
    Activations Density 0.018%

    No Known Activations