© 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. 247410
    Prev
    Next
    INDEX
    Explanations

    cases, logo, editorial, child

    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
    ਾ
    0.68
    ни
    0.59
    ي
    0.55
     спект
    0.54
    те
    0.52
     échanges
    0.50
    نى
    0.50
    生
    0.50
    ните
    0.49
    вел
    0.49
    POSITIVE LOGITS
    usik
    0.54
     Konstru
    0.51
    ową
    0.49
     co
    0.49
     KCl
    0.47
     Cosa
    0.47
     KF
    0.46
    ुलिस
    0.46
     WSA
    0.46
     Fe
    0.46
    Activations Density 0.000%

    No Known Activations