© 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. 29-GEMMASCOPE-2-RES-262K
    7. 147537
    Prev
    Next
    INDEX
    Explanations

    Experience Cloud

    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_29_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
     ವ್ಯ
    0.76
    চৈতন্য
    0.75
     baat
    0.70
     চৈতন্য
    0.70
    стом
    0.68
     guesswork
    0.66
    辖
    0.65
     Correspondence
    0.65
     لدى
    0.65
    ❝
    0.65
    POSITIVE LOGITS
    迴
    0.80
    挸
    0.68
    浩
    0.68
    耀
    0.67
     පමණ
    0.66
    يون
    0.66
     розмі
    0.64
    ဆက်
    0.63
     تغ
    0.63
     কাপড়
    0.62
    Activations Density 0.001%

    No Known Activations