© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2399
    Prev
    Next
    INDEX
    Explanations

    code snippet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !
    1.19
    !,
    1.02
    !;
    1.01
     perché
    0.99
     çünkü
    0.94
     jūs
    0.93
    !:
    0.93
    —
    0.91
     porque
    0.89
     because
    0.89
    POSITIVE LOGITS
     upto
    1.66
     atleast
    1.60
     learnt
    1.31
     respective
    1.31
     inbuilt
    1.30
     yg
    1.29
     dataframe
    1.27
     পরিমান
    1.25
     KYC
    1.24
    列
    1.22
    Activations Density 0.417%

    No Known Activations