© 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. 51747
    Prev
    Next
    INDEX
    Explanations

    find easily and cheap

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

    buying cheap and safe

    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
    ിച്ചത്
    0.53
    nię
    0.50
    𝕚
    0.49
    también
    0.49
    nEnter
    0.48
    ীভূত
    0.48
    <unused31>
    0.48
    scatterplot
    0.48
     ಏನು
    0.47
    stopper
    0.47
    POSITIVE LOGITS
     derivative
    0.48
     secund
    0.47
     vég
    0.47
     last
    0.46
     near
    0.45
    沙
    0.45
     comparison
    0.44
     buying
    0.44
     bez
    0.43
     Mercer
    0.43
    Activations Density 0.000%

    No Known Activations