© 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. 11842
    Prev
    Next
    INDEX
    Explanations

    DOA, SHD, ES, CTB, WRAP

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

    emission profiles, genetic variants, video RAM, SAP Controlling

    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
    uradaki
    0.43
     übrigens
    0.42
    还有一个
    0.39
    娱乐圈
    0.39
    还是
    0.38
    aphosa
    0.38
    据说
    0.38
    𝙛
    0.38
    还是很
    0.37
     اصلا
    0.37
    POSITIVE LOGITS
     actin
    0.45
     $>
    0.45
     \%
    0.43
     magnitudes
    0.42
     sheen
    0.42
     "
    0.41
     '
    0.41
     viscosity
    0.41
     $\
    0.41
    AS
    0.40
    Activations Density 0.048%

    No Known Activations