© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13214
    Prev
    Next
    INDEX
    Explanations

    numbers and statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    savvy
    0.32
     accolades
    0.30
     jargon
    0.30
    🈺
    0.30
    📟
    0.29
    🉐
    0.29
     dyslex
    0.29
     Obamacare
    0.29
     FTE
    0.29
    🈵
    0.28
    POSITIVE LOGITS
    0
    0.38
    2
    0.35
    3
    0.32
    4
    0.32
    5
    0.30
     the
    0.29
     a
    0.28
    6
    0.27
    1
    0.26
    9
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.