© 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-16K
    7. 6043
    Prev
    Next
    INDEX
    Explanations

    low, medium, high, quality indicators

    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_16k_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
     можете
    0.38
    百度
    0.36
    mael
    0.36
    पीय
    0.36
    zle
    0.35
    tpc
    0.35
    izo
    0.35
    ත
    0.34
     закон
    0.34
     LIGO
    0.34
    POSITIVE LOGITS
     vari
    0.51
     magnificent
    0.50
    Vari
    0.45
     hatched
    0.42
    ക്കാര
    0.41
    VIEWS
    0.40
    vari
    0.39
     prop
    0.39
    PROP
    0.39
     gian
    0.39
    Activations Density 0.029%

    No Known Activations