© 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. 240851
    Prev
    Next
    INDEX
    Explanations

    coming, vibrating, living, with tables

    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
     influent
    0.50
     natoque
    0.45
     descart
    0.44
     animados
    0.44
    䄸
    0.44
     expresión
    0.43
     celular
    0.43
     cuarent
    0.43
    缐
    0.43
     eldest
    0.43
    POSITIVE LOGITS
    OF
    0.51
    وض
    0.50
    MOND
    0.50
    SON
    0.46
    CLEAR
    0.46
    SHOW
    0.46
     स्कोर
    0.45
    X
    0.45
    ОВ
    0.44
     世界
    0.44
    Activations Density 0.001%

    No Known Activations