© 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. 138308
    Prev
    Next
    INDEX
    Explanations

    dealership nearby

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

    health, manufacturer, connectivity, results

    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
     mildly
    0.46
    具
    0.46
    Ꮸ
    0.44
     बू
    0.44
    までは
    0.42
    德
    0.42
     purged
    0.42
    ன
    0.41
    铍
    0.41
     maliciously
    0.41
    POSITIVE LOGITS
     واپسی
    0.46
     diharapkan
    0.45
     Laud
    0.42
     SUV
    0.41
    ंदोल
    0.40
    ण्याची
    0.40
     SUVs
    0.40
     UNICEF
    0.40
    submissions
    0.40
     بنات
    0.39
    Activations Density 0.003%

    No Known Activations