© 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. 1988
    Prev
    Next
    INDEX
    Explanations

    2017 onward

    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
    Young
    0.61
    One
    0.60
    :
    0.57
    Die
    0.56
    Several
    0.55
    im
    0.55
    <h2>
    0.54
    Tun
    0.54
    Histor
    0.53
    av
    0.53
    POSITIVE LOGITS
    ⃣
    0.83
    ″]
    0.80
     tradeoff
    0.77
     breakpoint
    0.77
     uptick
    0.75
     tweak
    0.74
    ′
    0.74
     fallback
    0.72
     timeframe
    0.72
    ″
    0.72
    Activations Density 0.233%

    No Known Activations