© 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. 7238
    Prev
    Next
    INDEX
    Explanations

    percentages and numbers

    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
     with
    0.38
    with
    0.37
    क्षेप
    0.37
    {\'
    0.35
    Mapping
    0.34
    gives
    0.34
    }$;
    0.33
    gens
    0.33
    agons
    0.33
    דו
    0.32
    POSITIVE LOGITS
    敌人
    0.35
     trei
    0.35
     ziren
    0.34
    ᴸ
    0.34
     oración
    0.33
     acquistare
    0.33
     iyi
    0.32
     doivent
    0.31
     GCC
    0.31
     gió
    0.31
    Activations Density 0.062%

    No Known Activations