© 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. 717
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation followed by word

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

    proper nouns after punctuation

    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
    送信
    0.28
     umfasst
    0.28
    崗
    0.27
    ೧
    0.26
    ೬
    0.26
    ೨
    0.25
     Eingang
    0.25
    ๑
    0.25
    ப்
    0.24
    lles
    0.24
    POSITIVE LOGITS
     అలాంటి
    0.27
     Bloomberg
    0.27
     activism
    0.26
     Quaker
    0.26
     similar
    0.25
     hacerlo
    0.25
     Hermione
    0.25
     যতটা
    0.24
    这一点
    0.24
    そういう
    0.24
    Activations Density 0.152%

    No Known Activations