© 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. 27121
    Prev
    Next
    INDEX
    Explanations

    with them

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

    costs and setup optimization

    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
    i
    0.67
    ad
    0.66
    oc
    0.60
    ing
    0.57
    om
    0.55
    is
    0.54
    v
    0.54
    he
    0.53
    ø
    0.53
    am
    0.53
    POSITIVE LOGITS
    ༈
    0.52
     thải
    0.50
    ใหญ
    0.49
     interesantes
    0.49
     lò
    0.49
     aportar
    0.49
     ferramentas
    0.48
     моду
    0.48
     tumbuhan
    0.48
    㜌
    0.48
    Activations Density 0.000%

    No Known Activations