© 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. 115156
    Prev
    Next
    INDEX
    Explanations

    observations I need

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

    simple answer

    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
     υ
    0.48
     waffle
    0.46
     tri
    0.44
     результата
    0.43
    alled
    0.43
    amplitude
    0.42
     भुला
    0.42
     amplitud
    0.42
     apariencia
    0.42
     Could
    0.41
    POSITIVE LOGITS
    开设
    0.46
    不稳定
    0.43
    QUAL
    0.42
    誅
    0.42
     বলেছেন
    0.42
    習
    0.41
    ற்க
    0.41
    आईएस
    0.41
    杀
    0.41
    데요
    0.41
    Activations Density 0.001%

    No Known Activations