© 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. 172285
    Prev
    Next
    INDEX
    Explanations

    practice, editor, dealers, fridge, configuration, renovations

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

    timing, duration, waiting

    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
    i
    0.46
    lateral
    0.45
     Lateral
    0.44
     frontier
    0.44
     proposed
    0.44
     ultimate
    0.43
     rightful
    0.43
     스스로
    0.42
     hulk
    0.42
     waiver
    0.41
    POSITIVE LOGITS
     సె
    0.50
     attendre
    0.49
     دقائق
    0.49
    分钟
    0.49
    濑
    0.49
     சிதம்ப
    0.47
    听到
    0.47
     đợi
    0.47
    ốt
    0.46
     seekBar
    0.46
    Activations Density 0.001%

    No Known Activations