© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80960
    Prev
    Next
    INDEX
    Explanations

    depending on factors

    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
    Negative Logits
    vano
    0.46
    霄
    0.45
    iba
    0.44
     لقب
    0.43
    近日
    0.43
     bodo
    0.43
    ომ
    0.42
     कंप्लीट
    0.41
    emer
    0.41
    ault
    0.40
    POSITIVE LOGITS
     expectation
    0.43
     expectations
    0.41
    ROLL
    0.41
    [,,"
    0.40
     канторы
    0.40
    =\""
    0.40
    दोनों
    0.40
     ensuing
    0.39
     nutritive
    0.39
    WaitingTime
    0.39
    Activations Density 0.004%

    No Known Activations