© 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. 47532
    Prev
    Next
    INDEX
    Explanations

    evaluating descriptions or statements

    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
    комо
    0.48
    Кон
    0.47
    С
    0.47
    ш
    0.46
    При
    0.45
    с
    0.45
    影响
    0.45
     причи
    0.43
    Forever
    0.42
    чку
    0.42
    POSITIVE LOGITS
     negotiations
    0.47
     deuterium
    0.46
     raport
    0.45
     exhausted
    0.45
     exhaustion
    0.43
     एक्चु
    0.42
     Redist
    0.41
     chamber
    0.41
     exhausts
    0.40
    🥃
    0.40
    Activations Density 0.015%

    No Known Activations