© 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. 27471
    Prev
    Next
    INDEX
    Explanations

    comparisons or states of matter

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

    numbers and units

    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
    רו
    0.57
    傃
    0.51
    墘
    0.51
    扂
    0.50
    ים
    0.50
    感動
    0.50
    נטי
    0.49
    фон
    0.48
    感动
    0.48
    俢
    0.47
    POSITIVE LOGITS
     Hg
    0.52
     Q
    0.49
     heaviest
    0.49
     epidemiological
    0.46
     $\
    0.46
     exploded
    0.46
     explosives
    0.45
     heavier
    0.45
     overweight
    0.45
     $
    0.44
    Activations Density 0.000%

    No Known Activations