© 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. 84573
    Prev
    Next
    INDEX
    Explanations

    brainstrust

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

    convert to or for

    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
    TxtArea
    0.50
     Tart
    0.49
     Ž
    0.49
     Bennett
    0.46
     Nose
    0.46
     حاجه
    0.46
     Jaw
    0.46
     ake
    0.46
    Ž
    0.46
     McF
    0.46
    POSITIVE LOGITS
    ῦ
    0.57
    enrich
    0.55
    وک
    0.54
    نم
    0.52
    ا
    0.52
    ی
    0.50
    یوں
    0.50
    엔
    0.50
    کار
    0.49
    インター
    0.49
    Activations Density 0.853%

    No Known Activations