© 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. 17-GEMMASCOPE-2-RES-16K
    7. 6482
    Prev
    Next
    INDEX
    Explanations

    activation and deactivation

    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_17_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
    полу
    0.75
    verbrauch
    0.74
     slags
    0.73
    ্রাজ
    0.73
    Resolver
    0.71
     visiteurs
    0.70
     felhasznál
    0.70
    멧
    0.68
     acabó
    0.67
    कुमार
    0.67
    POSITIVE LOGITS
     activation
    0.98
     Activation
    0.95
     concealment
    0.93
     disabling
    0.93
     activating
    0.92
     concealing
    0.92
     invisibility
    0.90
     unlocking
    0.90
     blockade
    0.90
     deactivate
    0.89
    Activations Density 0.197%

    No Known Activations