© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3882
    Prev
    Next
    INDEX
    Explanations

    file extension

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

    memcpy_ followed by underscore

    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_53_width_65k_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
    TGFuZ
    0.50
    MSFontService
    0.49
     ၊
    0.47
    ktCap
    0.45
    ाइवेट
    0.43
    âteau
    0.42
     onderwerp
    0.42
     সরাস
    0.42
    द्दी
    0.42
    রিতে
    0.42
    POSITIVE LOGITS
    _
    2.08
    \_
    1.32
    __
    1.16
    _*
    1.00
    _[
    0.98
    _%
    0.96
    _$
    0.96
    _${
    0.95
    _(
    0.95
    _<
    0.89
    Activations Density 0.072%

    No Known Activations