© 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. 54249
    Prev
    Next
    INDEX
    Explanations

    identifying `ID`, `Tags`, `Bangalore`, `workflow`

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

    figure out

    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
    </h2>
    0.56
     isl
    0.56
     into
    0.51
     in
    0.50
     indic
    0.49
     Ltd
    0.48
     excav
    0.47
     inti
    0.47
     educ
    0.46
     introductory
    0.46
    POSITIVE LOGITS
    мышлен
    0.48
    맘
    0.46
    嗉
    0.46
    الق
    0.45
    <0x99>
    0.45
    циях
    0.45
    蘇
    0.45
    omor
    0.45
    猢
    0.45
    лда
    0.45
    Activations Density 0.000%

    No Known Activations