© 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. 78566
    Prev
    Next
    INDEX
    Explanations

    language model

    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
     esperienza
    0.47
     linken
    0.46
     overruling
    0.44
     लिं
    0.44
     prostagland
    0.43
    引
    0.43
     Entwick
    0.42
     letz
    0.42
     crowning
    0.42
     spermatozoa
    0.42
    POSITIVE LOGITS
    IDE
    0.45
    avelength
    0.43
    '
    0.42
    2
    0.41
    1
    0.41
    CO
    0.40
    AV
    0.40
    US
    0.40
    AI
    0.40
    AVER
    0.40
    Activations Density 0.001%

    No Known Activations