© 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. 58049
    Prev
    Next
    INDEX
    Explanations

    plug hole

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

    especially football

    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
    ښ
    0.46
     étudi
    0.45
    >-</
    0.44
     triángulo
    0.44
    uhi
    0.44
     engend
    0.44
    aç
    0.41
     shum
    0.41
     puisse
    0.41
    ituary
    0.40
    POSITIVE LOGITS
    用户的
    0.50
     سنوات
    0.46
    ＰＥ
    0.44
     ಬ
    0.44
     안내
    0.44
    連接
    0.43
    摖
    0.42
    DEPARTMENT
    0.42
    PatientR
    0.42
     С
    0.41
    Activations Density 0.000%

    No Known Activations