© 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. 202326
    Prev
    Next
    INDEX
    Explanations

    image, print head, stabilizing

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

    conjunctions and descriptive categories

    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
     مثال
    0.50
    지
    0.49
    facility
    0.47
    로
    0.46
    رو
    0.46
    م
    0.45
    บ
    0.45
    小說
    0.44
     आखिर
    0.44
    بر
    0.44
    POSITIVE LOGITS
    ogue
    0.48
     Thì
    0.42
     Feldman
    0.42
     Bamb
    0.42
     Jó
    0.42
     Jackson
    0.41
     Guggenheim
    0.41
     tanned
    0.41
     则
    0.41
    ette
    0.41
    Activations Density 0.001%

    No Known Activations