© 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. 242672
    Prev
    Next
    INDEX
    Explanations

    injury or fatality

    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
     કહે
    0.51
     แต่
    0.50
     ক্রমাগত
    0.50
    方針
    0.50
    ೨
    0.49
    પો
    0.49
     Semarang
    0.49
     ২০
    0.48
     編
    0.48
     Departament
    0.48
    POSITIVE LOGITS
    .
    0.50
    an
    0.45
    .**
    0.42
    ttes
    0.41
    vette
    0.41
    urr
    0.41
    ®.
    0.39
    ان
    0.39
    ................
    0.39
    dul
    0.39
    Activations Density 0.001%

    No Known Activations