© 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. 21106
    Prev
    Next
    INDEX
    Explanations

    Available at/from URLs

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

    publicly available

    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
    ↵↵
    0.52
    ía
    0.48
    ano
    0.47
    ange
    0.46
    um
    0.46
    agem
    0.46
    into
    0.45
    in
    0.45
    il
    0.44
    io
    0.44
    POSITIVE LOGITS
    蟎
    0.42
     দলিল
    0.42
     баскет
    0.41
     ordinances
    0.41
     flapping
    0.41
     সম্পদের
    0.40
     اهم
    0.40
     或
    0.39
     документов
    0.39
     দ্রব
    0.38
    Activations Density 0.002%

    No Known Activations