© 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. 211009
    Prev
    Next
    INDEX
    Explanations

    died after

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

    complex explanations and solutions

    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
    耖
    0.46
     तसेच
    0.44
     मुख्यतः
    0.43
     ವೇ
    0.42
    人と
    0.42
     우리나라
    0.41
    SSL
    0.41
     srcset
    0.40
     এই
    0.39
     Wellbeing
    0.39
    POSITIVE LOGITS
     получа
    0.49
     soie
    0.44
    #(
    0.43
     mecz
    0.42
     [%
    0.41
     bulun
    0.41
    <0xB2>
    0.41
     Zimmerman
    0.41
     dies
    0.40
     mín
    0.40
    Activations Density 0.001%

    No Known Activations