© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135840
    Prev
    Next
    INDEX
    Explanations

    visual aspects

    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
     ނ
    0.52
    überkü
    0.47
    原始内容存档于
    0.44
    setIs
    0.44
    |,
    0.44
     არა
    0.43
    modelLogin
    0.43
     ಹೃ
    0.43
    subdir
    0.43
    archiwizowane
    0.43
    POSITIVE LOGITS
     meltdown
    0.50
    ్రి
    0.46
     mel
    0.45
     matar
    0.45
    ا
    0.45
    蜴
    0.45
    faktor
    0.44
     hours
    0.44
    絭
    0.44
    ाइ
    0.43
    Activations Density 0.000%

    No Known Activations