© 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. 74943
    Prev
    Next
    INDEX
    Explanations

    arbitrator, employee, or specific entity

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

    Melkor, Sauron, quest board

    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
    ブロ
    0.50
     financiero
    0.50
     financiera
    0.49
    金融
    0.48
    tvrt
    0.47
     signific
    0.46
     financieros
    0.46
    ン
    0.46
    Mike
    0.45
     financière
    0.44
    POSITIVE LOGITS
    affine
    0.47
     ellipsoid
    0.47
     изготов
    0.46
    latitude
    0.46
     outcrop
    0.45
     adipose
    0.45
     alleles
    0.44
    apparent
    0.44
     antibody
    0.44
     aesthetic
    0.44
    Activations Density 0.002%

    No Known Activations