© 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. 31-GEMMASCOPE-2-RES-262K
    4. 123686
    Prev
    Next
    INDEX
    Explanations

    fine wool, database, purpose, int, protons

    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_31_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
    不够
    0.44
     ջ
    0.43
    boldsymbol
    0.41
     warning
    0.41
    errno
    0.41
     errno
    0.40
    eh
    0.39
    ic
    0.39
    icherweise
    0.39
    act
    0.38
    POSITIVE LOGITS
    מ
    0.66
    კ
    0.50
    ಿದರು
    0.47
     alkal
    0.46
     yüz
    0.46
    تر
    0.45
    ב
    0.45
     convex
    0.44
    輸入
    0.43
    }}{\
    0.42
    Activations Density 0.001%

    No Known Activations