© 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. 244548
    Prev
    Next
    INDEX
    Explanations

    ideas, secrets, or reflection

    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
     منتقل
    0.48
     হয়ত
    0.48
     나올
    0.45
     reproducing
    0.44
     ممکن
    0.43
     يقوم
    0.43
    出一个
    0.43
    ]]).
    0.43
    -”
    0.43
    可能会
    0.43
    POSITIVE LOGITS
    month
    0.44
     ajo
    0.43
     famosa
    0.43
     cajas
    0.42
    кой
    0.42
     famoso
    0.40
     tierras
    0.40
    PURE
    0.40
    قيم
    0.40
     conocido
    0.40
    Activations Density 0.001%

    No Known Activations