© 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. 48209
    Prev
    Next
    INDEX
    Explanations

    people shopping

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

    Data profiling

    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
    είο
    0.60
    ه‌ای
    0.54
    ப்படு
    0.50
    ی
    0.49
    ┕
    0.49
    短暂
    0.47
    ंबू
    0.47
    प्ट
    0.47
    पणा
    0.46
    šo
    0.46
    POSITIVE LOGITS
     know
    0.48
     guards
    0.48
     majoring
    0.48
    manuel
    0.48
     duplicated
    0.48
     rusted
    0.46
    ?
    0.46
     emotionally
    0.45
     belong
    0.45
     urb
    0.44
    Activations Density 0.000%

    No Known Activations