© 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-262K
    7. 81386
    Prev
    Next
    INDEX
    Explanations

    virtual card

    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
     CRISPR
    0.47
    への
    0.43
    UEFA
    0.42
    िंग्स
    0.42
    画
    0.42
     procéd
    0.42
    ED
    0.42
     Figma
    0.41
     invis
    0.41
     dwRes
    0.41
    POSITIVE LOGITS
    ହି
    0.46
    smittel
    0.44
    лма
    0.43
    дку
    0.42
    лку
    0.42
    ᇁ
    0.42
    ０
    0.41
    墘
    0.41
    Fault
    0.40
    𝟬
    0.40
    Activations Density 0.008%

    No Known Activations