© 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-65K
    7. 62528
    Prev
    Next
    INDEX
    Explanations

    data loading and preprocessing

    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_65k_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
     Composition
    0.47
     strongest
    0.46
     on
    0.44
    composition
    0.44
     Indicator
    0.43
     Measurement
    0.40
    㘟
    0.40
     measurement
    0.40
     Substituting
    0.40
     Measuring
    0.39
    POSITIVE LOGITS
     povas
    0.43
    🥶
    0.43
    alámb
    0.42
     initialise
    0.41
     обновления
    0.41
     했던
    0.41
     идеально
    0.41
    iget
    0.40
     जाति
    0.40
    <unused1>
    0.40
    Activations Density 0.011%

    No Known Activations