© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 32065
    Prev
    Next
    INDEX
    Explanations

    west/east/north/south of

    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
     as
    0.75
     unwa
    0.75
     emberek
    0.74
    </b>
    0.73
    ooo
    0.70
     атмос
    0.70
    like
    0.69
    其他
    0.68
    lai
    0.67
    র
    0.67
    POSITIVE LOGITS
    '
    1.19
    ка
    0.88
    HD
    0.86
    ि
    0.79
    は
    0.77
    ADAS
    0.76
    даг
    0.75
    AK
    0.75
    FS
    0.75
    ्
    0.75
    Activations Density 0.005%

    No Known Activations