© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 89628
    Prev
    Next
    INDEX
    Explanations

    equine consumption; calmed down

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

    base case

    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
    /
    0.52
     maupun
    0.50
     nebo
    0.47
     Mich
    0.46
     Armor
    0.46
     atau
    0.45
    parte
    0.45
     and
    0.44
    र्
    0.44
     Deck
    0.44
    POSITIVE LOGITS
    了一眼
    0.48
    笘
    0.45
     ludicrous
    0.44
     ಜಿಲ್ಲ
    0.43
    !);
    0.43
    ﺲ
    0.43
    דת
    0.42
     horrid
    0.42
    )}$,
    0.41
    ﻞ
    0.41
    Activations Density 0.002%

    No Known Activations