© 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. 124147
    Prev
    Next
    INDEX
    Explanations

    financial contributions

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

    approaching the poles

    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
     anderes
    0.50
    었다
    0.49
     Киев
    0.46
    ings
    0.46
    ap
    0.45
     बताया
    0.45
    ม
    0.45
     quarks
    0.44
    irla
    0.44
    ंकन
    0.44
    POSITIVE LOGITS
    ږي
    0.50
    criar
    0.44
    木の
    0.44
    淳
    0.43
     dring
    0.43
    旱
    0.42
     ջ
    0.42
    ニーズ
    0.41
     renovate
    0.41
     kerosene
    0.39
    Activations Density 0.001%

    No Known Activations