© 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. 126005
    Prev
    Next
    INDEX
    Explanations

    company in, friends are, garden views

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

    Cartographer of the interior

    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
    шили
    0.49
    ঁপ
    0.47
    Цент
    0.45
    eşit
    0.45
    Ꮷ
    0.45
    腔
    0.44
    均为
    0.44
     شوق
    0.44
    车型
    0.43
    贩
    0.43
    POSITIVE LOGITS
     ocult
    0.49
     TERMIN
    0.48
     maze
    0.46
     alqu
    0.46
     নথি
    0.45
    ALCHEMY
    0.43
    PERATURE
    0.43
     about
    0.42
    PARTMENT
    0.42
     "~/
    0.41
    Activations Density 0.004%

    No Known Activations