© 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. 1607
    Prev
    Next
    INDEX
    Explanations

    . toInt, . clone

    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
     ]]
    0.84
    RouterModule
    0.72
     وال
    0.72
     गर्नुहोस्
    0.69
    шите
    0.68
     plumber
    0.68
    setForeground
    0.68
    ”]
    0.67
     αρκε
    0.67
    針對
    0.66
    POSITIVE LOGITS
    ToString
    1.49
    toString
    1.39
     toString
    1.22
    get
    1.09
    clone
    1.06
     ToString
    1.05
     clone
    1.02
     Get
    0.99
    ToStr
    0.98
    asInstanceOf
    0.94
    Activations Density 0.142%

    No Known Activations