© 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. 112119
    Prev
    Next
    INDEX
    Explanations

    rarely involves, was made, often involves, were designed

    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
    Ꮟ
    0.47
    ณี
    0.46
    愔
    0.46
    ที่คุณ
    0.46
    ानीय
    0.45
    เพราะ
    0.45
     आप
    0.45
    leston
    0.44
    癢
    0.44
    ដោយ
    0.44
    POSITIVE LOGITS
    த்துவ
    0.41
     denounced
    0.40
    platte
    0.39
    onde
    0.39
    HO
    0.39
    များကို
    0.39
    то
    0.39
     takip
    0.39
    ر
    0.39
     notre
    0.38
    Activations Density 0.001%

    No Known Activations