© 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. 201124
    Prev
    Next
    INDEX
    Explanations

    foregin words and technical terms

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

    prevent conflicts or forbid

    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
    ك
    0.77
    گ
    0.52
    درا
    0.50
    ش
    0.49
    ک
    0.48
    키
    0.48
    چ
    0.47
    ເລ
    0.46
    च
    0.46
    크
    0.46
    POSITIVE LOGITS
    AndWait
    0.50
    owanie
    0.48
    ovým
    0.47
    પૂર્ણ
    0.47
     zásobníku
    0.46
     αγο
    0.45
     品質
    0.45
     જેમ
    0.45
    <0xA7>
    0.44
    原子炉
    0.44
    Activations Density 0.002%

    No Known Activations