© 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. 44950
    Prev
    Next
    INDEX
    Explanations

    punctuation and specific words

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

    code punctuation followed by print

    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
    χρι
    0.43
    आईए
    0.42
    ბ
    0.42
    ри
    0.42
    ра
    0.41
    ती
    0.41
    ൪
    0.41
    ρι
    0.40
    crs
    0.40
     crap
    0.39
    POSITIVE LOGITS
     Yu
    0.41
    بغي
    0.38
     Saints
    0.38
     apporter
    0.38
     Modelling
    0.38
     Revenue
    0.38
     Yacht
    0.38
     Ef
    0.38
     Ordnance
    0.37
     Ornamental
    0.37
    Activations Density 0.000%

    No Known Activations