© 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. 219222
    Prev
    Next
    INDEX
    Explanations

    able to

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

    (Chorus)

    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
     giovane
    0.53
     giovani
    0.52
    Spawner
    0.49
    <unused31>
    0.49
    মিক্যাল
    0.48
    铛
    0.48
     prodotti
    0.48
    மாவட்ட
    0.47
    侨
    0.47
    এড
    0.47
    POSITIVE LOGITS
    ing
    0.50
    That
    0.50
     diat
    0.48
     Earlier
    0.47
     Pred
    0.47
     multim
    0.47
    out
    0.46
     Predict
    0.46
     expir
    0.46
    at
    0.46
    Activations Density 0.001%

    No Known Activations