© 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. 14335
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by common phrases

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

    sentence starters

    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
     ،
    0.42
    ，
    0.40
     ，
    0.40
    ،
    0.37
    ，「
    0.37
    ၊
    0.35
     ፣
    0.33
    $,
    0.33
     Ә
    0.32
     、
    0.32
    POSITIVE LOGITS
     be
    0.29
     it
    0.29
    usta
    0.24
     njima
    0.23
    its
    0.23
     sadly
    0.23
     in
    0.23
     have
    0.22
    的美
    0.22
     jejich
    0.22
    Activations Density 0.060%

    No Known Activations