© 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. 150516
    Prev
    Next
    INDEX
    Explanations

    ice machine

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

    evaluating conditions and boundaries

    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
     જરૂરી
    0.49
    Registre
    0.48
     चैंपियनशिप
    0.48
     اخبار
    0.47
     सके
    0.47
     Prayers
    0.46
    职责
    0.45
    蚪
    0.45
     দিয়
    0.45
     Tjiwarl
    0.45
    POSITIVE LOGITS
     aeration
    0.58
     amusement
    0.57
     erop
    0.54
     luxury
    0.52
     embarrassment
    0.52
     computation
    0.51
     annoyance
    0.51
     intercalation
    0.51
     cooling
    0.50
     erosion
    0.50
    Activations Density 0.000%

    No Known Activations