© 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. 2484
    Prev
    Next
    INDEX
    Explanations

    bolding text with asterisks

    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
    <unused85>
    0.87
    brellas
    0.80
     finitely
    0.79
    }});
    0.75
     enumerate
    0.75
     pairs
    0.74
     GmbH
    0.74
    瀣
    0.74
     plc
    0.74
     lx
    0.73
    POSITIVE LOGITS
    <b>
    3.01
    <strong>
    2.98
     **
    2.38
    **
    1.70
    <u>
    1.69
    mathbf
    1.61
     {\
    1.51
     ***
    1.43
    <h3>
    1.40
    <h4>
    1.38
    Activations Density 1.670%

    No Known Activations