© 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. 131590
    Prev
    Next
    INDEX
    Explanations

    accurate measurements, accidental discharges/dividers

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

    angle, depth, mass, type

    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
     GoObject
    0.52
    记住
    0.50
     খানের
    0.49
    晞
    0.48
    纮
    0.48
    对抗
    0.48
    婍
    0.47
    责任
    0.47
     দায়িত্ব
    0.46
    改编
    0.46
    POSITIVE LOGITS
     cob
    0.49
    SETTINGS
    0.48
    CHEMICAL
    0.47
    sekten
    0.46
     by
    0.46
    CONFIG
    0.46
     six
    0.45
    chemical
    0.45
     geist
    0.45
    "@
    0.44
    Activations Density 0.000%

    No Known Activations