© 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. 175035
    Prev
    Next
    INDEX
    Explanations

    medical conditions

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

    reclamation, claiming

    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
    نت
    0.53
    糉
    0.47
    髋
    0.46
    زالة
    0.46
    angaroo
    0.46
    篾
    0.44
     Turt
    0.44
     Pizza
    0.43
     Restaurants
    0.43
     Kathmandu
    0.43
    POSITIVE LOGITS
    룀
    0.55
     diga
    0.52
     একের
    0.45
    あい
    0.43
     troph
    0.41
     unbe
    0.40
     ég
    0.40
     bathed
    0.39
                 
    0.39
     dưỡng
    0.39
    Activations Density 0.000%

    No Known Activations