© 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. 2091
    Prev
    Next
    INDEX
    Explanations

    code examples and data formatting

    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
     ⠀
    0.76
    (?)
    0.75
     (?)
    0.71
    enging
    0.67
    atera
    0.65
     combination
    0.64
    घात
    0.64
    áte
    0.63
     (.)
    0.62
    ≲
    0.62
    POSITIVE LOGITS
     abc
    1.37
    abc
    1.36
    foo
    1.21
     foo
    1.21
     ABC
    1.16
    ABC
    1.13
     Eiffel
    1.08
     manzanas
    1.06
    banana
    1.05
     elef
    1.03
    Activations Density 1.466%

    No Known Activations