© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15942
    Prev
    Next
    INDEX
    Explanations

    assign and process data

    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
    as
    0.68
    ada
    0.63
    ap
    0.59
    z
    0.58
    als
    0.55
    producing
    0.54
    nis
    0.54
    um
    0.52
    ia
    0.52
    ci
    0.52
    POSITIVE LOGITS
     Karten
    0.47
    НИЕ
    0.47
    Ꮂ
    0.47
     Между
    0.46
     Gerry
    0.46
     uważ
    0.45
     Treiber
    0.45
    ссив
    0.45
     Tutor
    0.45
     Tried
    0.45
    Activations Density 0.025%

    No Known Activations