© 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. 3033
    Prev
    Next
    INDEX
    Explanations

    technical entities and their functions

    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
    ,
    0.65
     throughout
    0.64
    ependant
    0.63
     وعلى
    0.62
     despite
    0.60
     través
    0.58
     Trotz
    0.58
     несмотря
    0.57
     através
    0.57
    </tr>
    0.56
    POSITIVE LOGITS
     نشوف
    0.62
     לך
    0.59
     looked
    0.58
     bootstrapping
    0.57
    esque
    0.57
     felt
    0.57
     kinda
    0.56
    ኤ
    0.55
     كنت
    0.55
    考虑
    0.55
    Activations Density 0.104%

    No Known Activations