© 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. 4428
    Prev
    Next
    INDEX
    Explanations

    It explains actions

    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
     tersebut
    0.60
    .'
    0.57
     अथवा
    0.55
     interacts
    0.55
     ity
    0.53
     ili
    0.51
     nebo
    0.51
    s
    0.51
     acquires
    0.51
    others
    0.50
    POSITIVE LOGITS
     sneaky
    0.59
     Allow
    0.56
     permitió
    0.55
     allowing
    0.55
    讓
    0.55
     messy
    0.54
    Allow
    0.53
    让你
    0.52
    ทำให้
    0.51
    讓你
    0.50
    Activations Density 0.153%

    No Known Activations