© 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. 89432
    Prev
    Next
    INDEX
    Explanations

    Sunday morning

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

    filenames and contacts

    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
     pancreatic
    0.46
     probabilistic
    0.45
    लित
    0.45
     कैंसर
    0.44
    <0x91>
    0.44
     პრო
    0.43
     %>
    0.43
    కుంటు
    0.43
     criada
    0.43
     healer
    0.43
    POSITIVE LOGITS
    ，
    0.48
    évén
    0.45
    нием
    0.45
     スタッドレスタイヤ
    0.45
     Nit
    0.44
    qr
    0.43
     Entscheidung
    0.43
    俭
    0.43
    شون
    0.43
    هایت
    0.43
    Activations Density 0.000%

    No Known Activations