© 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. 224990
    Prev
    Next
    INDEX
    Explanations

    comfort and ease

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

    explain *what*

    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
     ނ
    0.50
     горе
    0.48
     delegates
    0.46
    जारत
    0.45
    lı
    0.45
     ค่ะ
    0.45
     redirectTo
    0.45
     ㅛ
    0.45
     coda
    0.45
     н
    0.45
    POSITIVE LOGITS
    ଣ୍
    0.49
    ্যেষ্ঠ
    0.47
    Campe
    0.46
     Cub
    0.45
    nehmen
    0.44
     Replace
    0.43
     Watches
    0.43
    wendung
    0.43
    based
    0.43
     bauen
    0.43
    Activations Density 0.001%

    No Known Activations