© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 11513
    Prev
    Next
    INDEX
    Explanations

    Daily Mail percent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Beef
    0.49
     perfused
    0.48
     consecutivos
    0.43
    Trails
    0.42
     carboxyl
    0.41
     perfusion
    0.41
     ohmic
    0.41
    🤙
    0.41
     axially
    0.40
     beef
    0.40
    POSITIVE LOGITS
     Mail
    0.61
    Mail
    0.48
     mail
    0.46
    mail
    0.43
     MAIL
    0.43
    дет
    0.43
     British
    0.42
     '
    0.41
     ';
    0.40
    MAIL
    0.40
    Activations Density 0.011%

    No Known Activations