© 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. 77725
    Prev
    Next
    INDEX
    Explanations

    buyer will be obliged

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

    actions followed by results

    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
    ོན་
    0.50
    ましたが
    0.48
     pancreas
    0.47
    역
    0.46
     किश
    0.46
    ங்கும்
    0.45
    몹
    0.45
     likewise
    0.45
    ቤ
    0.45
    엡
    0.45
    POSITIVE LOGITS
    stä
    0.48
     Amal
    0.48
     původ
    0.48
     Dijk
    0.48
     slog
    0.46
     सेतु
    0.46
     Calvary
    0.46
     Astros
    0.45
    avad
    0.44
     håll
    0.44
    Activations Density 0.002%

    No Known Activations