© 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-262K
    7. 5333
    Prev
    Next
    INDEX
    Explanations

    globes, Addresses, beast

    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_262k_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
     top
    0.51
     respective
    0.42
     instrumental
    0.42
     pens
    0.41
     do
    0.41
     k
    0.41
     s
    0.40
     National
    0.39
     Compass
    0.39
     Spine
    0.39
    POSITIVE LOGITS
    ۸
    0.81
    <unused2023>
    0.81
    ۴
    0.80
    ٨
    0.80
    quantidade
    0.80
    <unused2100>
    0.79
     获取
    0.79
    <unused234>
    0.79
    २
    0.79
    ječ
    0.79
    Activations Density 0.000%

    No Known Activations