© 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. 60866
    Prev
    Next
    INDEX
    Explanations

    little office, about what, one of

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

    ChatGPT and PostgreSQL

    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
    ϒ
    0.47
     gitt
    0.45
    uset
    0.41
     suppos
    0.41
     diap
    0.40
     physique
    0.39
    IPO
    0.39
    φ
    0.39
     gid
    0.38
     geos
    0.38
    POSITIVE LOGITS
     Servicios
    0.50
    導數
    0.47
    ٣
    0.46
     Jetty
    0.46
    ೩
    0.45
    دست
    0.45
     सीएचएसएल
    0.45
     आइकॉन
    0.44
    ১৬
    0.44
    แต่
    0.43
    Activations Density 0.000%

    No Known Activations