© 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. 44847
    Prev
    Next
    INDEX
    Explanations

    specific scripts

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

    connected to wireless networks

    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
    忓
    0.50
    ช่วยเหลือ
    0.46
     (\%)
    0.45
    ets
    0.42
     chr
    0.42
    VIEWS
    0.42
     lt
    0.41
     lle
    0.41
     prenant
    0.40
     Insulin
    0.40
    POSITIVE LOGITS
    ओं
    0.49
     dissection
    0.48
     పరీ
    0.48
    getLong
    0.46
    ses
    0.46
     получа
    0.46
     دام
    0.45
    ኛ
    0.45
    assembled
    0.44
     ہماری
    0.44
    Activations Density 0.000%

    No Known Activations