© 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. 2673
    Prev
    Next
    INDEX
    Explanations

    return

    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
     congress
    0.82
     Congress
    0.80
     पुस्तिका
    0.75
    Ⴝ
    0.73
    亚洲
    0.71
    congress
    0.70
     elles
    0.69
    ຊ
    0.69
     한국
    0.68
    ვის
    0.68
    POSITIVE LOGITS
    return
    4.87
     return
    4.82
     Return
    4.15
    Return
    3.84
     returns
    3.73
     returning
    3.68
     RETURN
    3.63
     returned
    3.62
    返回
    3.57
     Returning
    3.34
    Activations Density 0.707%

    No Known Activations