© 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. 236645
    Prev
    Next
    INDEX
    Explanations

    commendable

    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
     પણ
    0.48
     Largest
    0.47
     බැ
    0.47
     mailing
    0.44
     on
    0.44
     আমরা
    0.44
     Connector
    0.44
    ᐋ
    0.43
     CONNE
    0.43
     सादर
    0.42
    POSITIVE LOGITS
    BREAK
    0.53
    satisf
    0.48
    Após
    0.47
    匆
    0.45
     Paola
    0.44
    Przy
    0.44
    <0x0E>
    0.44
     transt
    0.43
    得分
    0.43
    影
    0.43
    Activations Density 0.001%

    No Known Activations