© 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-65K
    7. 15856
    Prev
    Next
    INDEX
    Explanations

    technical documentation and code snippets

    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
    ت
    0.52
    ில்
    0.50
    على
    0.49
    تھی
    0.48
    ת
    0.48
    Pentru
    0.46
    بیل
    0.45
     ricord
    0.45
    Questa
    0.44
    When
    0.44
    POSITIVE LOGITS
    位的
    0.45
    <0xC2>
    0.43
     находиться
    0.43
    డీపీ
    0.41
    发的
    0.41
    ilaian
    0.39
    UNK
    0.39
    在
    0.38
    GTBase
    0.38
    igators
    0.38
    Activations Density 0.001%

    No Known Activations