© 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. 165147
    Prev
    Next
    INDEX
    Explanations

    company status

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

    no runtime overhead

    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
    ｒ
    0.51
    klik
    0.49
    ução
    0.48
    íz
    0.48
    棣
    0.48
    ície
    0.47
    itzt
    0.47
    za
    0.47
    šten
    0.47
     continúa
    0.47
    POSITIVE LOGITS
    一线
    0.48
    ندی
    0.48
    आन
    0.47
    शुभ
    0.47
     Tracer
    0.47
    著名的
    0.47
     narration
    0.46
    敍
    0.46
     nondegenerate
    0.45
     ADS
    0.45
    Activations Density 0.001%

    No Known Activations