© 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. 110947
    Prev
    Next
    INDEX
    Explanations

    after word, then word

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

    terminal, other states, challenges

    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
    ियर्स
    0.50
    स्तिक
    0.44
    ühm
    0.43
    ua
    0.42
    ttä
    0.42
    ਾ
    0.42
     खासकर
    0.41
    ázquez
    0.41
    ੱਚ
    0.41
    澈
    0.41
    POSITIVE LOGITS
     ဗ
    0.49
     гос
    0.48
     podremos
    0.47
     তিনটি
    0.46
     Yangzhou
    0.46
     государственной
    0.46
     เตรียม
    0.46
     อี
    0.45
     недостаточно
    0.45
     Okamoto
    0.45
    Activations Density 0.002%

    No Known Activations