© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 46116
    Prev
    Next
    INDEX
    Explanations

    days ago or from

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

    experimental drug

    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
    اط
    0.50
    খার
    0.50
    ൊ
    0.50
    ק
    0.49
     Shortcut
    0.48
    اخت
    0.45
    도시
    0.45
    סת
    0.45
    פל
    0.44
    чих
    0.43
    POSITIVE LOGITS
    ថ្ង
    0.58
    ienced
    0.50
     صدای
    0.50
     ▼
    0.48
     பதிவு
    0.47
    vi
    0.47
     существует
    0.47
     treating
    0.47
     დღ
    0.46
     phía
    0.46
    Activations Density 0.001%

    No Known Activations