© 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. 113234
    Prev
    Next
    INDEX
    Explanations

    an eight-mile-long swath

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

    specific punctuation and formatting

    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
     ulike
    0.56
     vanligt
    0.51
     brukes
    0.50
     bruke
    0.48
     दुनिया
    0.48
    Perry
    0.48
    ៦
    0.47
     黃
    0.46
    ُوا
    0.45
     saranam
    0.45
    POSITIVE LOGITS
    κών
    0.46
     exquis
    0.45
     une
    0.45
    ില്‍
    0.44
    ကျ
    0.42
    uité
    0.42
    πάν
    0.42
    </tbody>
    0.41
    算
    0.41
    숙
    0.41
    Activations Density 0.000%

    No Known Activations