© 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. 7141
    Prev
    Next
    INDEX
    Explanations

    specific places and technical terms

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

    I am digging a hole

    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
     phosphorylated
    0.18
     daar
    0.17
    antaranya
    0.16
    रिडोर
    0.15
     glycer
    0.15
    ^{*}=\
    0.15
     tubules
    0.15
     esters
    0.15
     möj
    0.15
     cathodes
    0.15
    POSITIVE LOGITS
    ри
    0.16
    ...
    0.15
     […]
    0.14
    ;
    0.14
    <unused2186>
    0.14
    п
    0.14
    郑
    0.14
    все
    0.14
    澳门
    0.14
    <unused2031>
    0.14
    Activations Density 3.747%

    No Known Activations