© 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. 85601
    Prev
    Next
    INDEX
    Explanations

    discussions and meetings

    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
    ва
    1.09
    е
    1.02
    ie
    0.96
    fehl
    0.95
    ok
    0.88
    ak
    0.86
    in
    0.84
    เป็น
    0.82
    xs
    0.82
    ft
    0.78
    POSITIVE LOGITS
     nella
    0.76
    diği
    0.72
    اتها
    0.71
     držav
    0.69
    ই
    0.67
     nelle
    0.66
     nový
    0.66
     funcion
    0.66
    焔
    0.66
    ல்
    0.65
    Activations Density 0.000%

    No Known Activations