© 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. 80188
    Prev
    Next
    INDEX
    Explanations

    filing dates and details

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

    someone who

    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
    filter
    0.50
    h
    0.49
    art
    0.49
    filling
    0.49
    za
    0.48
    pot
    0.48
    und
    0.48
    po
    0.47
    find
    0.47
    ert
    0.46
    POSITIVE LOGITS
     سيكون
    0.52
    ︾
    0.50
    应
    0.49
     должен
    0.49
    нечно
    0.47
     chắc
    0.47
     виртуа
    0.47
     đèn
    0.47
     παιδιά
    0.47
    堬
    0.46
    Activations Density 0.001%

    No Known Activations