© 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. 1734
    Prev
    Next
    INDEX
    Explanations

    governance and processing

    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
    ණය
    0.89
    ασία
    0.88
    பம்
    0.87
     auditions
    0.84
     Begriff
    0.83
    යක්
    0.83
    쨰
    0.83
     homosexuality
    0.83
    ськ
    0.82
    größe
    0.82
    POSITIVE LOGITS
    forward
    0.83
    解决方案
    0.79
    estimator
    0.78
    -
    0.77
     instructional
    0.76
    biotic
    0.74
    focused
    0.74
    onomic
    0.73
    folding
    0.72
    Forward
    0.71
    Activations Density 0.711%

    No Known Activations