© 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. 87462
    Prev
    Next
    INDEX
    Explanations

    after eating or digesting

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

    Google shows

    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
     على
    0.44
     ações
    0.44
     comunicación
    0.44
     pleg
    0.44
     ensino
    0.43
     ò
    0.43
     говорил
    0.43
     contribuer
    0.42
    <unused2156>
    0.42
     לי
    0.41
    POSITIVE LOGITS
    Pdf
    0.47
    <%=
    0.46
    āju
    0.46
    !.
    0.45
    akhir
    0.43
    çı
    0.43
    Appearance
    0.42
    Kamu
    0.42
    ნის
    0.42
    </a>
    0.42
    Activations Density 0.001%

    No Known Activations