© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5166
    Prev
    Next
    INDEX
    Explanations

    save and run code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    면
    0.60
    case
    0.58
    职务
    0.56
    어도
    0.54
     Carne
    0.54
    luc
    0.54
     संकट
    0.53
    1
    0.52
    zuführen
    0.52
    Ark
    0.52
    POSITIVE LOGITS
    buildSpec
    0.80
    <unused967>
    0.80
    }.")
    0.79
    炁
    0.78
     चम्मच
    0.77
     पाठशाला
    0.77
     hires
    0.76
    <unused193>
    0.76
    <unused1922>
    0.75
    謦
    0.75
    Activations Density 0.055%

    No Known Activations