© 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. 80450
    Prev
    Next
    INDEX
    Explanations

    definitions and contexts

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

    records broken, shape holds well

    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
    疳
    0.45
     Toma
    0.44
     problemática
    0.43
     अथवा
    0.43
     situada
    0.43
     तरल
    0.43
     அல்லது
    0.42
    )».
    0.42
     जाने
    0.42
    难题
    0.42
    POSITIVE LOGITS
    ಧ್ಯ
    0.52
    y
    0.51
    ح
    0.49
    maps
    0.47
     scaffolds
    0.46
    ית
    0.46
    ଲ
    0.46
    ER
    0.46
    namespaces
    0.45
    মি
    0.45
    Activations Density 0.000%

    No Known Activations