© 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-16K
    7. 2310
    Prev
    Next
    INDEX
    Explanations

    URLs and website names

    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_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
     subTest
    1.08
     Mostrar
    1.00
    ␊
    0.98
    GULD
    0.96
     Elektrokh
    0.96
    <unused2153>
    0.96
    ehicle
    0.95
    <unused592>
    0.93
     secuencia
    0.93
     Elektrokhimiya
    0.93
    POSITIVE LOGITS
     https
    0.99
    https
    0.95
     YouTube
    0.88
     www
    0.86
    www
    0.85
     http
    0.84
    http
    0.83
    facebook
    0.83
    youtube
    0.80
     Google
    0.79
    Activations Density 0.073%

    No Known Activations