© 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. 61989
    Prev
    Next
    INDEX
    Explanations

    error handling

    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
    kách
    0.43
    werke
    0.41
    기에
    0.40
     וא
    0.38
    kona
    0.38
    <0xE1>
    0.38
    ."[
    0.38
     Dünya
    0.37
     Comisión
    0.37
    Dem
    0.37
    POSITIVE LOGITS
     substituting
    0.49
     alte
    0.48
     amenable
    0.45
     antar
    0.44
     anionic
    0.43
     negatives
    0.43
     tepung
    0.42
     `:`,
    0.42
     innovating
    0.41
     doable
    0.41
    Activations Density 0.068%

    No Known Activations