© 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. 9-GEMMASCOPE-2-RES-16K
    7. 1919
    Prev
    Next
    INDEX
    Explanations

    early stages of processes

    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_9_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
     awk
    2.82
    욱
    2.71
     plummet
    2.66
    Dylan
    2.62
    ಿರ
    2.60
    ền
    2.59
    wavelength
    2.57
    しく
    2.56
    های
    2.55
    GreaterThan
    2.53
    POSITIVE LOGITS
     adopters
    3.08
    pä
    2.92
    ْد
    2.84
     lamented
    2.79
     fastened
    2.74
    ньому
    2.74
    IENCE
    2.67
     dönem
    2.66
    siniz
    2.63
     всего
    2.59
    Activations Density 0.190%

    No Known Activations