© 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. 221675
    Prev
    Next
    INDEX
    Explanations

    pain, commercial, best, liter, late, bin

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

    profit;

    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
    il
    0.60
    ir
    0.53
     promul
    0.52
    ל
    0.49
    tvrt
    0.49
    ;}
    0.48
    ן
    0.48
     уточ
    0.47
     promulg
    0.47
    ]].
    0.46
    POSITIVE LOGITS
    Hotkey
    0.42
    ﻹ
    0.41
     watts
    0.41
    LensFlare
    0.41
     Música
    0.40
    맞
    0.40
    滥
    0.40
     الأص
    0.40
     Farbe
    0.39
    ColorF
    0.39
    Activations Density 0.000%

    No Known Activations