© 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. 58045
    Prev
    Next
    INDEX
    Explanations

    splash panel; panels; until

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

    dates, metadata, basics, foundation

    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
     হন
    0.50
     není
    0.48
     ନ
    0.48
     nemá
    0.48
     گردد
    0.47
     末
    0.47
     ہے۔
    0.46
     ():
    0.46
    ُونَ
    0.46
     problemática
    0.46
    POSITIVE LOGITS
    יי
    0.55
    tgt
    0.53
    ט
    0.49
     the
    0.48
     Clem
    0.46
     you
    0.46
    ในการ
    0.46
    טע
    0.45
    สม
    0.45
     piloting
    0.45
    Activations Density 0.000%

    No Known Activations