© 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. 30594
    Prev
    Next
    INDEX
    Explanations

    preliminary, delicious, stack

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

    negation or adverse outcomes

    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
     اجرای
    0.48
    י
    0.48
     વર્
    0.47
    次に
    0.47
     예배
    0.47
    手册
    0.47
     Рэ
    0.46
     તમારે
    0.46
    改装
    0.46
    accessToken
    0.46
    POSITIVE LOGITS
     (
    0.51
    ,
    0.50
     muscul
    0.47
    3
    0.47
    MO
    0.46
     parten
    0.45
    SC
    0.45
     DEFIN
    0.44
     druk
    0.44
    STA
    0.43
    Activations Density 0.000%

    No Known Activations