© 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. 37220
    Prev
    Next
    INDEX
    Explanations

    you notified by

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

    consumer hardware and CPUs

    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
    今の
    0.48
    
    0.46
    嵓
    0.46
    崦
    0.46
     выражения
    0.46
     маъ
    0.46
    ন্ধে
    0.45
    arre
    0.45
    क्की
    0.45
    ͹
    0.45
    POSITIVE LOGITS
     ország
    0.47
     converg
    0.46
     orbit
    0.45
     España
    0.45
     bina
    0.43
     optima
    0.43
     indul
    0.42
    Duration
    0.42
     beautifully
    0.42
     pól
    0.41
    Activations Density 0.000%

    No Known Activations