© 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. 31-GEMMASCOPE-2-RES-65K
    7. 48895
    Prev
    Next
    INDEX
    Explanations

    lung for, whimsical and, watching someone

    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_65k_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
    hindi
    0.38
     restrict
    0.37
    切り
    0.37
    數據
    0.37
     commen
    0.36
    の
    0.36
    overrightarrow
    0.35
    RS
    0.35
     کی
    0.35
     polynomial
    0.34
    POSITIVE LOGITS
     Fleetwood
    0.38
     Radcliffe
    0.36
     модуль
    0.36
    阎
    0.35
    giers
    0.34
    Фран
    0.34
    涹
    0.34
     kring
    0.34
     Amos
    0.33
     NPC
    0.33
    Activations Density 0.001%

    No Known Activations