© 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. 150275
    Prev
    Next
    INDEX
    Explanations

    Eve Online

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

    hydrothermal vents

    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
     conflitto
    0.52
    Portada
    0.49
    によって
    0.46
    ლ
    0.46
    لاع
    0.45
    И
    0.45
    挟
    0.45
    ﻞ
    0.44
     صفحات
    0.44
     জেনারেল
    0.44
    POSITIVE LOGITS
     चिक
    0.46
    åg
    0.45
     liquors
    0.45
    ril
    0.44
     baking
    0.43
     æ
    0.43
    knit
    0.43
    acil
    0.43
    osar
    0.43
    ed
    0.43
    Activations Density 0.000%

    No Known Activations