© 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. 51465
    Prev
    Next
    INDEX
    Explanations

    processes and completion

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

    describing attributes or quantities

    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
     triángulos
    0.50
    𝐼
    0.48
     Broken
    0.46
     Porque
    0.45
     Trois
    0.45
     बिकॉज
    0.45
    Всім
    0.44
    崧
    0.44
     أبي
    0.44
     Oiseaux
    0.44
    POSITIVE LOGITS
     envisaged
    0.43
     examined
    0.42
    as
    0.41
     recep
    0.40
    ৎস
    0.40
     integrated
    0.39
     computationally
    0.39
    ttps
    0.39
    census
    0.39
    slidesPerGroup
    0.39
    Activations Density 0.000%

    No Known Activations