© 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. 191428
    Prev
    Next
    INDEX
    Explanations

    Dumb Ways to Die

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

    tutorials and guides

    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
    rel
    0.44
    ki
    0.43
     thereafter
    0.43
    지
    0.41
    ere
    0.40
    ess
    0.40
    builtin
    0.40
    kka
    0.39
     successivamente
    0.39
    bundle
    0.39
    POSITIVE LOGITS
     mario
    0.53
     אם
    0.48
     첫
    0.46
     гидро
    0.45
     여러
    0.45
    这种
    0.44
     ():
    0.44
     italian
    0.44
     Tutorial
    0.44
     如何
    0.43
    Activations Density 0.000%

    No Known Activations