© 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. 119420
    Prev
    Next
    INDEX
    Explanations

    telecom, software, brands, and programming

    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
     .*
    0.44
    ட்
    0.38
     PLC
    0.36
    artifact
    0.35
    maid
    0.35
    怿
    0.35
    পূর্ব
    0.35
     infrequent
    0.35
    }\\
    0.35
     해당
    0.35
    POSITIVE LOGITS
    上看
    0.42
     apă
    0.41
    潾
    0.38
    𝕆
    0.37
     latino
    0.37
     мог
    0.37
    廡
    0.37
     ژوند
    0.36
    亨
    0.36
     atlas
    0.36
    Activations Density 0.000%

    No Known Activations