© 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. 19675
    Prev
    Next
    INDEX
    Explanations

    domain availability

    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
     Darrell
    0.46
    颅
    0.44
    нер
    0.43
     đọc
    0.42
    opencamera
    0.41
     شدن
    0.41
    urf
    0.40
     mật
    0.40
     代码
    0.40
    cipher
    0.40
    POSITIVE LOGITS
    D
    0.55
    DA
    0.51
    W
    0.51
    FI
    0.47
     three
    0.46
    1
    0.46
    HI
    0.46
     Слова
    0.44
    '
    0.44
    3
    0.44
    Activations Density 0.001%

    No Known Activations