© 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. 61334
    Prev
    Next
    INDEX
    Explanations

    authority over

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

    clickbait titles

    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
    career
    0.50
    ה
    0.48
    ा
    0.48
    a
    0.47
    Rogers
    0.47
     stimuli
    0.45
    Public
    0.45
    ಠ
    0.44
     論
    0.43
    Palmer
    0.43
    POSITIVE LOGITS
     měli
    0.50
     ermöglicht
    0.49
    imut
    0.45
     hosszú
    0.45
     měla
    0.45
     leichte
    0.44
    ومو
    0.44
    غاز
    0.44
     hadden
    0.44
     kunde
    0.43
    Activations Density 0.000%

    No Known Activations