© 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. 208509
    Prev
    Next
    INDEX
    Explanations

    immediate vicinity

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

    numbered lists

    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
     مرتبط
    0.52
     Pha
    0.50
     γ
    0.49
     PHA
    0.48
     rencontré
    0.47
     فيما
    0.46
     ৩৩
    0.46
     bring
    0.46
     χα
    0.46
     φ
    0.44
    POSITIVE LOGITS
    וד
    0.48
    PIN
    0.48
    วัน
    0.46
    Pada
    0.45
    न्यास
    0.45
    มือ
    0.44
     Dayan
    0.44
    นี้
    0.44
    이를
    0.44
    歩
    0.44
    Activations Density 0.001%

    No Known Activations