© 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. 216383
    Prev
    Next
    INDEX
    Explanations

    work, day, stains, praising, account

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

    Doesn't work or is essential

    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
     члены
    0.52
     представлена
    0.50
     имена
    0.50
     પટે
    0.50
     प्रतिनिधियों
    0.50
     फोर्स
    0.49
    <unused520>
    0.49
    бах
    0.49
    <unused516>
    0.49
     контакта
    0.49
    POSITIVE LOGITS
    C
    0.50
     diving
    0.45
     meeting
    0.45
     states
    0.45
    注释
    0.44
     phosphorylation
    0.43
     Schrödinger
    0.43
    ਜ
    0.43
     syn
    0.42
     handling
    0.42
    Activations Density 0.000%

    No Known Activations