© 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. 51248
    Prev
    Next
    INDEX
    Explanations

    opportunities, friend, 7, similar, GNU, interact

    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
     famiglie
    0.48
     GeoNames
    0.46
     corriente
    0.43
    爿
    0.43
     மூன்று
    0.43
     nowych
    0.42
     lingue
    0.42
    panorama
    0.42
     moléculas
    0.42
     nových
    0.41
    POSITIVE LOGITS
     inconsistency
    0.43
     ena
    0.43
     train
    0.43
     自
    0.43
     注意
    0.43
    Bunch
    0.43
    съ
    0.42
    сня
    0.42
    ing
    0.41
     audacity
    0.41
    Activations Density 0.011%

    No Known Activations