© 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. 183786
    Prev
    Next
    INDEX
    Explanations

    grown studio started article comparison tends

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

    I'm a language model

    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
    ере
    0.47
    اض
    0.45
    сторінку
    0.45
    wurf
    0.45
    מע
    0.45
    小
    0.44
    冠
    0.44
    추
    0.43
    不到
    0.42
    auten
    0.42
    POSITIVE LOGITS
    тные
    0.45
     ہوا۔
    0.45
     টেল
    0.45
     mãos
    0.44
     कूलर
    0.44
     Tribes
    0.43
     inhibit
    0.43
     हात
    0.42
     ਕਿਸ
    0.42
     subsided
    0.42
    Activations Density 0.000%

    No Known Activations