© 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. 97290
    Prev
    Next
    INDEX
    Explanations

    end of phrase / sentence

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

    sometimes

    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
    悠
    0.45
    惘
    0.45
    TryGetValue
    0.45
     kuin
    0.43
    不少
    0.41
    ıllı
    0.41
     souvent
    0.41
    avis
    0.41
    你去
    0.41
    议
    0.41
    POSITIVE LOGITS
     CLOSE
    0.48
     CLOS
    0.48
     cerrar
    0.45
     escaped
    0.44
    يج
    0.44
    समा
    0.44
     insecticides
    0.43
     colaboradores
    0.42
     ISLAND
    0.42
     condense
    0.42
    Activations Density 0.000%

    No Known Activations