© 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. 4361
    Prev
    Next
    INDEX
    Explanations

    URLs and markdown lists

    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
    全都
    0.88
    izziness
    0.78
     genitals
    0.76
     сиг
    0.74
     majeur
    0.73
     冖
    0.73
     snelheid
    0.73
     firepower
    0.73
    নকে
    0.71
    득
    0.71
    POSITIVE LOGITS
    Wikipedia
    1.40
    Numerous
    1.32
    Youtube
    1.30
    Google
    1.29
    YouTube
    1.28
    Various
    1.28
     Wikipedia
    1.27
     стаття
    1.25
     Videos
    1.20
     YouTube
    1.19
    Activations Density 0.165%

    No Known Activations