© 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. 5486
    Prev
    Next
    INDEX
    Explanations

    of the other

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

    brief synopsis, facing us, key themes, more linear

    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
    ו
    0.55
     tipo
    0.50
     neka
    0.50
     zid
    0.48
    other
    0.47
    ĸ
    0.47
    وید
    0.47
    </strong>
    0.46
     deti
    0.46
     njih
    0.46
    POSITIVE LOGITS
     টেনে
    0.47
    幕
    0.47
     목적
    0.46
     EVP
    0.46
     फल
    0.46
     FRONT
    0.46
    摖
    0.45
     overw
    0.45
     WINDOW
    0.45
    篙
    0.45
    Activations Density 0.000%

    No Known Activations