© 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-16K
    7. 13112
    Prev
    Next
    INDEX
    Explanations

    deals for

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

    short note

    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_16k_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
    사회
    0.47
    жли
    0.43
     AIP
    0.43
    се
    0.42
    SUN
    0.40
     banded
    0.40
    터
    0.39
    lda
    0.39
     اکتوبر
    0.38
    द
    0.38
    POSITIVE LOGITS
     výraz
    0.61
     bestaat
    0.59
    ഡിയോ
    0.55
     nemá
    0.54
     タイ
    0.53
     geeft
    0.53
    があり
    0.52
     zák
    0.51
     utilizza
    0.51
     liggen
    0.50
    Activations Density 0.007%

    No Known Activations