© 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. 231723
    Prev
    Next
    INDEX
    Explanations

    internationally recognised or certified

    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
    과
    0.51
    Ỏ
    0.49
     teammates
    0.46
    Ś
    0.46
     buys
    0.45
     tweaks
    0.45
    在
    0.45
    Cav
    0.44
    སྐ
    0.44
    אה
    0.43
    POSITIVE LOGITS
     Prozess
    0.53
    GENER
    0.53
    ounced
    0.50
     Schwier
    0.48
    r
    0.45
     Vorteil
    0.45
    rir
    0.44
    uer
    0.44
    antemente
    0.43
    kte
    0.43
    Activations Density 0.001%

    No Known Activations