© 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. 245308
    Prev
    Next
    INDEX
    Explanations

    we have found

    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
    oss
    0.49
    隷
    0.46
     COMPLEXES
    0.45
    arch
    0.45
     bxc
    0.45
    rectangular
    0.44
    nee
    0.44
    idf
    0.43
    agg
    0.43
    redis
    0.43
    POSITIVE LOGITS
     एजेंट
    0.48
    痫
    0.48
     preços
    0.47
    投诉
    0.46
     Faktor
    0.45
     إ
    0.44
     banyak
    0.44
    粉丝
    0.44
     yardım
    0.43
     Psic
    0.43
    Activations Density 0.002%

    No Known Activations