© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28967
    Prev
    Next
    INDEX
    Explanations

    disciplines and examples

    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
    S
    0.63
    h
    0.59
    al
    0.55
    Property
    0.53
    a
    0.53
    C
    0.52
    R
    0.50
    re
    0.50
    le
    0.50
    Column
    0.49
    POSITIVE LOGITS
     volumes
    0.46
     disciplinas
    0.45
     exemplaire
    0.45
     グリーン
    0.44
     ござい
    0.43
     planification
    0.43
     Fmat
    0.43
     échelle
    0.43
     efficacement
    0.43
     repercussions
    0.43
    Activations Density 0.001%

    No Known Activations