© 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. 2134
    Prev
    Next
    INDEX
    Explanations

    also known as

    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
     also
    3.43
    also
    3.18
     Also
    3.14
    Also
    3.10
     также
    3.05
     भी
    2.87
     também
    2.82
    ও
    2.82
     también
    2.79
     også
    2.78
    POSITIVE LOGITS
     noteworthy
    1.74
     notable
    1.66
     самое
    1.65
     불구하고
    1.61
     বটে
    1.61
     merupakan
    1.42
    ष्
    1.41
    तरी
    1.40
    らった
    1.33
     importantly
    1.31
    Activations Density 0.073%

    No Known Activations