© 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. 62252
    Prev
    Next
    INDEX
    Explanations

    academic potential

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

    symbol sequence, shadow DOM, Vram

    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
    rolling
    0.49
    ローラ
    0.46
    授
    0.44
    IoT
    0.44
     IoT
    0.43
    structured
    0.42
     macromolecules
    0.42
    André
    0.41
     Schrödinger
    0.41
     matrices
    0.41
    POSITIVE LOGITS
     Auswahl
    0.49
    HIDE
    0.49
     нужны
    0.49
    ออนไลน์
    0.47
     ");
    0.46
     查询
    0.46
     нужен
    0.46
    ទទ
    0.46
     点击
    0.46
    喎
    0.46
    Activations Density 0.001%

    No Known Activations