© 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. 224173
    Prev
    Next
    INDEX
    Explanations

    Mattress features

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

    core free

    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
    ভালো
    0.55
     шкі
    0.54
     причине
    0.52
     в
    0.49
     গলায়
    0.48
     разработки
    0.48
     kwenye
    0.47
     обуча
    0.47
    цију
    0.47
     السبب
    0.46
    POSITIVE LOGITS
    oise
    0.45
    perform
    0.45
    សំ
    0.45
    kina
    0.45
    aim
    0.44
    centrum
    0.44
    o
    0.43
     Callaghan
    0.43
    ally
    0.42
    hesda
    0.42
    Activations Density 0.003%

    No Known Activations