© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 80462
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words

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

    review, legal, confirm, misuse

    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
    Y
    0.50
    ATCH
    0.49
    LOCK
    0.49
    WG
    0.46
    Alaska
    0.46
    YO
    0.46
    IM
    0.46
    WE
    0.45
    Â
    0.45
    AR
    0.44
    POSITIVE LOGITS
     محاس
    0.50
     данных
    0.50
     porcent
    0.48
     llevaba
    0.46
    सास
    0.46
    டப்பட்டது
    0.46
    ючи
    0.45
     дані
    0.45
     sayıda
    0.45
     apunta
    0.44
    Activations Density 0.000%

    No Known Activations