© 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. 91532
    Prev
    Next
    INDEX
    Explanations

    security, risk, or liability

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

    forecast numbers

    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
    )]:
    0.52
    THREE
    0.49
     memungkinkan
    0.48
    ORIES
    0.47
     সমাধান
    0.47
     regalo
    0.46
     trzy
    0.45
    yoruz
    0.45
    ുന്ന
    0.45
     wedge
    0.45
    POSITIVE LOGITS
    é
    0.53
    спонд
    0.48
     Sé
    0.47
    ik
    0.46
     cé
    0.45
    ens
    0.45
    bott
    0.45
     Thé
    0.44
     Jeh
    0.44
     Léon
    0.44
    Activations Density 0.000%

    No Known Activations