© 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-262K
    7. 203257
    Prev
    Next
    INDEX
    Explanations

    Sections and anatomy descriptions

    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
    OnFileChange
    0.46
    ifes
    0.45
    出
    0.44
     تريد
    0.42
     odv
    0.42
     البد
    0.41
     例如
    0.41
     понимаю
    0.41
    %:
    0.41
     conflit
    0.40
    POSITIVE LOGITS
    ленная
    0.48
    ிஸ்த
    0.47
     Pemer
    0.46
     Sept
    0.46
     to
    0.46
     Medical
    0.45
    лата
    0.45
    是为了
    0.43
     Assessment
    0.43
     observers
    0.42
    Activations Density 0.009%

    No Known Activations