© 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. 2747
    Prev
    Next
    INDEX
    Explanations

    gone or done

    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
     removing
    0.69
     discarding
    0.66
     detach
    0.64
    removing
    0.64
     disconnecting
    0.64
     stripping
    0.62
     incom
    0.61
     #-}
    0.61
     допуска
    0.61
     weaken
    0.60
    POSITIVE LOGITS
     gone
    2.77
     Gone
    2.40
    gone
    2.22
    Gone
    2.16
     done
    1.56
    Done
    1.55
     DONE
    1.55
    done
    1.52
     Done
    1.50
    DONE
    1.47
    Activations Density 0.289%

    No Known Activations