© 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. 112449
    Prev
    Next
    INDEX
    Explanations

    places, sunlight, events, Instagram, Rodr

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

    comic book, social media, managers, teachers

    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
     obese
    0.50
     skyscraper
    0.49
     セミ
    0.48
     pari
    0.48
     கப்ப
    0.48
     paramagnetic
    0.47
     ./
    0.47
     /.
    0.47
     quies
    0.46
     '/')
    0.46
    POSITIVE LOGITS
    די
    0.53
    Ř
    0.52
    ל
    0.50
    Regarding
    0.50
    צ
    0.50
    Instagram
    0.48
    ลักษณะ
    0.47
    Rodr
    0.46
    יו
    0.46
    Cómo
    0.46
    Activations Density 0.001%

    No Known Activations