© 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. 58204
    Prev
    Next
    INDEX
    Explanations

    optionseaside

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

    making observations and assessments

    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
    RELATES
    0.48
     lepiej
    0.47
     pono
    0.46
    姑娘
    0.45
    ERAL
    0.45
    FAX
    0.44
     券
    0.43
     lccn
    0.43
     ஏற்படுத்து
    0.43
    sinya
    0.42
    POSITIVE LOGITS
    ↵
    0.48
     Caribbean
    0.48
     Seaside
    0.46
     Andromeda
    0.44
     Santorini
    0.44
     Cosmic
    0.43
     Phoenix
    0.42
    ing
    0.42
    ↵↵
    0.42
     Eden
    0.42
    Activations Density 0.000%

    No Known Activations