© 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. 245551
    Prev
    Next
    INDEX
    Explanations

    between words and 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
    朐
    0.48
    Blade
    0.45
    Diagnosis
    0.45
     Gladi
    0.44
     स्वयं
    0.44
    Sword
    0.44
    Complaint
    0.44
    Biography
    0.43
    ानंतर
    0.43
    पाली
    0.43
    POSITIVE LOGITS
     和
    0.53
    தையும்
    0.50
     thiab
    0.48
    和
    0.48
    以及
    0.46
    等地
    0.46
     completeness
    0.46
     morphisms
    0.45
     也
    0.45
     ಮತ್ತು
    0.45
    Activations Density 0.000%

    No Known Activations