© 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. 1596
    Prev
    Next
    INDEX
    Explanations

    alternatives and choices

    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
    -
    0.95
    os
    0.94
    ow
    0.90
    ot
    0.90
    al
    0.89
    ade
    0.88
    :
    0.88
    ha
    0.88
    ized
    0.87
    hal
    0.85
    POSITIVE LOGITS
     optionally
    1.54
     bottomRight
    1.32
     juga
    1.32
     tambien
    1.30
     também
    1.26
     outra
    1.22
    それに
    1.22
     secondly
    1.19
     tambahan
    1.19
     ardından
    1.18
    Activations Density 0.577%

    No Known Activations