© 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. 4968
    Prev
    Next
    INDEX
    Explanations

    as a role or substitution

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

    as a

    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
     që
    0.22
     säger
    0.21
     vattati
    0.20
    ப்படுகிறது
    0.19
    ५
    0.19
     असून
    0.19
     cuja
    0.19
     која
    0.19
     daß
    0.18
     බව
    0.18
    POSITIVE LOGITS
     a
    0.29
     an
    0.29
     "
    0.21
     alternative
    0.19
     “
    0.19
    a
    0.19
     Source
    0.19
     incentive
    0.18
    ,
    0.18
     ‘
    0.18
    Activations Density 0.383%

    No Known Activations