© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3197
    Prev
    Next
    INDEX
    Explanations

    resources for links

    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_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
     resource
    0.76
     res
    0.75
    ToString
    0.74
     Res
    0.74
     origins
    0.73
    res
    0.73
    resource
    0.72
     🤔
    0.71
     düşünü
    0.70
     Based
    0.69
    POSITIVE LOGITS
    provide
    0.95
     linked
    0.95
    linked
    0.94
     permitirá
    0.91
     providing
    0.91
     fornecer
    0.91
    提供了
    0.88
     poświę
    0.86
     proporciona
    0.86
    provides
    0.85
    Activations Density 0.085%

    No Known Activations