© 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. 111437
    Prev
    Next
    INDEX
    Explanations

    Let phrase

    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
    années
    0.44
     tahun
    0.43
    鐗
    0.41
    ouched
    0.41
    rzym
    0.41
    为了
    0.40
     į
    0.39
    sliders
    0.38
     ধ
    0.38
     puzzles
    0.38
    POSITIVE LOGITS
     REF
    0.36
     EB
    0.35
     acetylcholine
    0.35
     ಎಸ್
    0.35
     Sense
    0.35
    效益
    0.35
    콤
    0.35
     Yield
    0.34
     resourceful
    0.34
    ژه
    0.34
    Activations Density 0.002%

    No Known Activations