© 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. 83429
    Prev
    Next
    INDEX
    Explanations

    numbers or specific phrases

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

    recognizing the next step

    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
    Ron
    0.54
    T
    0.49
     Хабаров
    0.48
    q
    0.47
    kih
    0.47
    Dio
    0.45
    V
    0.45
    DETAIL
    0.45
    x
    0.44
    ۶
    0.44
    POSITIVE LOGITS
     seyd
    0.48
     gør
    0.47
     iguais
    0.46
     probleml
    0.46
     kaks
    0.46
    神经
    0.45
    եմ
    0.44
    өм
    0.44
     soient
    0.43
     handelt
    0.42
    Activations Density 0.000%

    No Known Activations