© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 12813
    Prev
    Next
    INDEX
    Explanations

    en-us/

    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
     collision
    0.58
     part
    0.54
    Collision
    0.53
     collisions
    0.52
    time
    0.52
    号
    0.52
    喜
    0.51
     રિ
    0.48
    makers
    0.48
     infinite
    0.48
    POSITIVE LOGITS
     मार्ट
    0.75
    ecek
    0.69
     Martine
    0.69
     abnorm
    0.69
     GTI
    0.67
    KeyEvent
    0.66
     bunnies
    0.66
     crebre
    0.66
     nourish
    0.65
     Martina
    0.64
    Activations Density 0.005%

    No Known Activations