© 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. 224019
    Prev
    Next
    INDEX
    Explanations

    places and titles

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

    stating what is known

    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
    ʽ
    0.47
    iconfont
    0.44
     TextInputLayout
    0.41
    onDidChange
    0.41
     problème
    0.40
     Recherche
    0.39
     مقابلہ
    0.39
     মাঝারি
    0.38
    ݨ
    0.38
    🧔
    0.38
    POSITIVE LOGITS
     invas
    0.47
    今年
    0.46
     Федера
    0.43
    શ્વ
    0.43
    Од
    0.43
    我们
    0.42
     thrown
    0.41
     trá
    0.41
     leaders
    0.41
     leadership
    0.41
    Activations Density 0.000%

    No Known Activations