© 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. 97737
    Prev
    Next
    INDEX
    Explanations

    insert, up, subject, stock, relationship

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

    brow furrowed, sequence, snack while, image covers

    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
     Nai
    0.52
     Morty
    0.52
    ቂ
    0.50
    뻥
    0.50
     oublier
    0.48
     Bhan
    0.48
    씌
    0.47
     Dhan
    0.47
    unie
    0.47
     Bhojpuri
    0.46
    POSITIVE LOGITS
    time
    0.48
     conversion
    0.47
    TIME
    0.47
     controlar
    0.45
     اف
    0.44
     α
    0.44
    ylate
    0.44
     তৎকালীন
    0.43
    race
    0.43
     births
    0.43
    Activations Density 0.002%

    No Known Activations