© 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. 5127
    Prev
    Next
    INDEX
    Explanations

    re- followed by action

    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
    -\
    0.67
    po
    0.62
     standing
    0.61
     socios
    0.61
     देण्यात
    0.61
    Standing
    0.60
    sci
    0.60
    cook
    0.59
     অষ্টম
    0.57
     packed
    0.57
    POSITIVE LOGITS
     slows
    0.86
    kjav
    0.83
     slowed
    0.81
    raisal
    0.80
    铊
    0.78
     الفعل
    0.77
     बैटरी
    0.76
    বাচক
    0.76
     gặp
    0.75
    OrFail
    0.75
    Activations Density 0.039%

    No Known Activations