© 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. 19009
    Prev
    Next
    INDEX
    Explanations

    code insertion or listing

    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
    倞
    0.47
    ່ຽ
    0.45
    al
    0.43
    ба
    0.42
     énergétique
    0.42
     почув
    0.42
    ic
    0.42
     ч
    0.41
    ిక
    0.41
    ia
    0.41
    POSITIVE LOGITS
    <unused1103>
    0.47
     RCB
    0.46
     McKin
    0.45
     Bingham
    0.45
     Kanban
    0.44
     sincron
    0.41
    デニム
    0.41
     Boll
    0.41
    IGH
    0.40
     Davison
    0.40
    Activations Density 0.001%

    No Known Activations