© 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. 210791
    Prev
    Next
    INDEX
    Explanations

    pushchair, technology, fabric, way

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

    writing, code, and technical details

    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
     formul
    0.44
     http
    0.44
     greenish
    0.43
     https
    0.43
     pic
    0.42
     exclusivity
    0.41
     cellular
    0.41
    か
    0.41
     phiên
    0.40
     hospitalization
    0.40
    POSITIVE LOGITS
     люблю
    0.50
     Kurn
    0.50
     любовь
    0.48
     tuku
    0.48
     टिका
    0.48
    То
    0.47
     Нов
    0.47
    কল
    0.47
     Southerners
    0.47
    ierst
    0.47
    Activations Density 0.000%

    No Known Activations