© 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. 120568
    Prev
    Next
    INDEX
    Explanations

    disappeared, believe, report

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

    plan creation and commercial use

    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
    scrollView
    0.49
    斥
    0.48
     વાંચો
    0.47
    茎
    0.47
    꺽
    0.47
    пси
    0.46
    ப்பர்
    0.46
    扇
    0.46
    навли
    0.46
    assertSame
    0.45
    POSITIVE LOGITS
     on
    0.55
     panor
    0.53
     mund
    0.51
     hist
    0.49
     connex
    0.49
     situ
    0.48
     zuz
    0.48
     soz
    0.48
    धाम
    0.47
     n
    0.47
    Activations Density 0.001%

    No Known Activations