© 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. 243710
    Prev
    Next
    INDEX
    Explanations

    valuable, always, essential, surprise, performance, Vancouver, public, unique

    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
    𝙉
    0.50
    procedure
    0.48
    elingen
    0.48
     photoshop
    0.47
    $\,.
    0.44
    EIN
    0.43
     dye
    0.43
    UTES
    0.43
     contributions
    0.43
     haircut
    0.43
    POSITIVE LOGITS
     Franch
    0.55
     iar
    0.52
     kä
    0.51
    且
    0.49
     Burial
    0.47
     inac
    0.47
    诘
    0.47
    側に
    0.46
    छि
    0.46
    ă
    0.46
    Activations Density 0.000%

    No Known Activations