© 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. 47718
    Prev
    Next
    INDEX
    Explanations

    criteria and principles

    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
    H
    0.57
    D
    0.54
    Y
    0.54
    G
    0.53
    U
    0.52
    UR
    0.49
    L
    0.49
    P
    0.47
    8
    0.47
    0
    0.47
    POSITIVE LOGITS
     Politiker
    0.59
    ట్స్‌మన్
    0.49
     combatir
    0.48
    觎
    0.47
     políticas
    0.47
     melawan
    0.46
     আক্রমন
    0.46
     oraș
    0.45
     politič
    0.45
    ുകളിൽ
    0.45
    Activations Density 0.005%

    No Known Activations