© 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. 16-GEMMASCOPE-2-RES-262K
    7. 31863
    Prev
    Next
    INDEX
    Explanations

    adjust, adjustments

    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_16_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
    4
    0.64
     payroll
    0.62
     percorso
    0.56
     roll
    0.55
     denomination
    0.54
     mezzanine
    0.52
    ർത്ത
    0.52
     בה
    0.51
     playlists
    0.51
     rollover
    0.50
    POSITIVE LOGITS
    y
    0.64
    seau
    0.63
    ippy
    0.59
    îtier
    0.57
    લ
    0.56
    ियों
    0.55
    lere
    0.53
     tres
    0.52
    新的
    0.52
    abhave
    0.52
    Activations Density 0.001%

    No Known Activations