© 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. 216437
    Prev
    Next
    INDEX
    Explanations

    listed, services, appearance, exposed, hierarchies

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

    confused with others

    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
    鸫
    0.51
     fáb
    0.50
     거
    0.50
     事業
    0.48
     所以
    0.47
     每个
    0.46
     அப்பா
    0.46
     禁止
    0.46
     chính
    0.46
     已
    0.46
    POSITIVE LOGITS
    ushroom
    0.44
    zeta
    0.42
    женной
    0.42
    ₦
    0.40
     আঁচ
    0.40
    อย่างไร
    0.40
    rox
    0.39
    irit
    0.38
    の頃
    0.38
     Sadie
    0.38
    Activations Density 0.001%

    No Known Activations