© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65500
    Prev
    Next
    INDEX
    Explanations

    Epub doi

    np_acts-logits-general · gemini-2.5-flash-lite

    support bands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يج
    0.52
    僥
    0.46
    נה
    0.45
    真是
    0.44
    나는
    0.44
     ভারতবর্ষ
    0.43
     আশ্চর্য
    0.43
    螟
    0.43
    櫸
    0.43
    libexec
    0.42
    POSITIVE LOGITS
     Umar
    0.52
     currants
    0.51
     medi
    0.49
     xxx
    0.48
     shamb
    0.48
     oats
    0.48
     ammonia
    0.47
     conv
    0.47
     cheeses
    0.47
     raisins
    0.46
    Activations Density 0.000%

    No Known Activations