© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 88997
    Prev
    Next
    INDEX
    Explanations

    Harvey Miller, Harvey Nash, harvesting

    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_16_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
    й
    1.23
    اری
    1.20
    会
    1.18
    ли
    1.12
    ется
    1.09
    ナ
    1.01
    ೊ
    1.00
     postérieures
    0.99
    不
    0.99
    すすめ
    0.98
    POSITIVE LOGITS
    '
    1.71
    in
    1.68
    स
    1.42
    a
    1.32
    ↵↵
    1.30
    es
    1.30
    sons
    1.25
    s
    1.25
    ه
    1.20
     Harvey
    1.15
    Activations Density 0.002%

    No Known Activations