© 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. 25850
    Prev
    Next
    INDEX
    Explanations

    to be or interface is

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

    lawlessness increasing

    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
     daly
    0.51
    ersburg
    0.50
     ஓடுப
    0.50
     fă
    0.48
    ’
    0.48
     관광
    0.47
    atari
    0.47
    Ị
    0.46
    ící
    0.46
    ņ
    0.46
    POSITIVE LOGITS
    我
    0.54
    新
    0.50
    、
    0.48
     मुद्दों
    0.47
    setTime
    0.46
    রস
    0.46
    陳
    0.44
    結
    0.42
    肉
    0.42
    意識
    0.41
    Activations Density 0.000%

    No Known Activations