© 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. 32156
    Prev
    Next
    INDEX
    Explanations

    java import statements

    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
    畠
    0.40
    桔
    0.38
     страда
    0.37
     খোঁজ
    0.36
    ச்சா
    0.34
    ailangan
    0.34
    <unused1008>
    0.34
    の時間
    0.33
    祝い
    0.33
     viola
    0.33
    POSITIVE LOGITS
    dimension
    0.39
     극
    0.38
    uzu
    0.36
    isse
    0.35
    memset
    0.35
    releases
    0.34
    LR
    0.34
    λ
    0.34
    慮
    0.33
    LW
    0.33
    Activations Density 0.001%

    No Known Activations