© 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. 57203
    Prev
    Next
    INDEX
    Explanations

    items, objects, or places

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

    attacks, weaknesses

    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
    銀行
    0.47
    ו
    0.45
     म्हणून
    0.44
    ራት
    0.44
     올려
    0.43
     krijg
    0.43
    裁判
    0.43
     Patrim
    0.42
     stellt
    0.41
    👆
    0.41
    POSITIVE LOGITS
    áférés
    0.54
    connection
    0.45
    दोनों
    0.45
    thru
    0.45
     ecuación
    0.44
    ended
    0.44
    listener
    0.43
     XHTML
    0.43
    shared
    0.43
    siswa
    0.43
    Activations Density 0.000%

    No Known Activations