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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137392
    Prev
    Next
    INDEX
    Explanations

    lists of examples or definitions

    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
    o
    0.50
     magyar
    0.46
     konsult
    0.44
    奥
    0.44
    制造
    0.44
    面积
    0.44
    作り
    0.42
     Citizenship
    0.41
    ا
    0.41
    市区
    0.41
    POSITIVE LOGITS
     accordingly
    0.49
    }}-\
    0.47
     careless
    0.47
    Gos
    0.47
     Дэ
    0.45
     carelessly
    0.43
    ϲ
    0.43
    <0x0D>
    0.43
    }-\
    0.43
     substantially
    0.42
    Activations Density 0.005%

    No Known Activations