© 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. 30981
    Prev
    Next
    INDEX
    Explanations

    must notify, high sensitivity, very painful

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

    yo mama jokes

    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
     tiki
    0.51
     مسجد
    0.46
     tiket
    0.43
     salari
    0.42
    і
    0.42
     rẻ
    0.41
    硋
    0.41
     sampai
    0.41
     wɔ
    0.41
     konsumen
    0.41
    POSITIVE LOGITS
    Diffuse
    0.46
    SAFER
    0.46
    rische
    0.42
    hyd
    0.42
    Intro
    0.41
     கூறிய
    0.40
    旨在
    0.40
    Ⓜ
    0.40
     Initialize
    0.40
    nth
    0.40
    Activations Density 0.000%

    No Known Activations