© 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. 68740
    Prev
    Next
    INDEX
    Explanations

    phénomène, asth, nogle, 屋

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

    purpose of combine benefit goal

    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
     Proton
    0.46
     Ariz
    0.45
     धमाल
    0.45
    माश
    0.41
     Defenders
    0.41
     conformance
    0.41
     Ticket
    0.40
    伝
    0.39
    🐞
    0.39
     Braves
    0.39
    POSITIVE LOGITS
     بعض
    0.50
     屋
    0.47
     kür
    0.47
    asth
    0.46
    வை
    0.46
     phénomène
    0.46
    ształ
    0.45
     ontst
    0.45
    uo
    0.45
     quién
    0.44
    Activations Density 0.000%

    No Known Activations