© 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. 161710
    Prev
    Next
    INDEX
    Explanations

    ending phrases

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

    structure parsing

    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
    ise
    0.52
    </h4>
    0.51
    *
    0.48
     gaan
    0.46
    罢
    0.45
    </h3>
    0.44
    8
    0.44
    !
    0.44
     عندما
    0.44
    ilt
    0.43
    POSITIVE LOGITS
     해당
    0.52
     complicating
    0.48
     yǒu
    0.46
     નિર્ણય
    0.46
     Deleg
    0.45
     乀
    0.45
     Eucalyptus
    0.45
     Coleoptera
    0.45
    মী
    0.44
    事物
    0.44
    Activations Density 0.000%

    No Known Activations