© 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. 204094
    Prev
    Next
    INDEX
    Explanations

    foreign and technical words

    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
    ：
    0.41
    Traffic
    0.40
    Grunt
    0.40
    School
    0.40
     constructions
    0.40
    Axes
    0.40
    COMP
    0.39
    ?
    0.39
    项目
    0.39
    koh
    0.39
    POSITIVE LOGITS
    alez
    0.45
     жены
    0.43
    uels
    0.41
    ieder
    0.41
    olation
    0.41
     المنت
    0.41
    adio
    0.40
    amethasone
    0.40
     encore
    0.39
     보니
    0.39
    Activations Density 0.001%

    No Known Activations