© 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. 111567
    Prev
    Next
    INDEX
    Explanations

    running, charging, natural, public

    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
     ľudí
    0.51
    .¹
    0.42
     lidí
    0.41
     irão
    0.41
    жнему
    0.41
     சுற்றுச்சூழ
    0.41
     aqueles
    0.40
    ើយ
    0.40
    福祉
    0.40
    だと思う
    0.39
    POSITIVE LOGITS
     이번
    0.45
     part
    0.44
     complement
    0.40
     half
    0.37
     '
    0.36
     Complement
    0.36
     extension
    0.36
     Actor
    0.35
     송
    0.35
     جزء
    0.34
    Activations Density 0.002%

    No Known Activations