© 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. 26260
    Prev
    Next
    INDEX
    Explanations

    other amounts, the geek

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

    Norwich, Lancashire, Oxfordshire

    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
    طر
    0.50
    にする
    0.48
    በ
    0.48
    בש
    0.47
     boldly
    0.47
    ஜன்
    0.47
     Shash
    0.47
    Monday
    0.46
    ങ്ക്
    0.46
    ஜ்
    0.46
    POSITIVE LOGITS
     άν
    0.47
     సొ
    0.43
     সত্যিই
    0.41
     నాకు
    0.39
     YO
    0.39
     అతను
    0.39
    izzeria
    0.38
     И
    0.38
     Norwich
    0.38
    <unused28>
    0.38
    Activations Density 0.000%

    No Known Activations