© 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. 43076
    Prev
    Next
    INDEX
    Explanations

    fatal outcomes

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

    death as a consequence

    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
     التي
    0.45
    ・
    0.42
    /
    0.41
     которые
    0.40
     /
    0.39
    }/{
    0.39
     તેમના
    0.38
     customizations
    0.38
     theyre
    0.38
    里的
    0.37
    POSITIVE LOGITS
    取决
    0.49
    짧
    0.45
    ವೂ
    0.44
    ᆢ
    0.43
    双方
    0.41
    것도
    0.41
    ცა
    0.41
    вичайно
    0.41
    ㄿ
    0.41
     astute
    0.40
    Activations Density 0.001%

    No Known Activations