© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 148550
    Prev
    Next
    INDEX
    Explanations

    harmless piece, noise robustness

    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
    helle
    0.83
    }){
    0.81
     অবাধ
    0.80
    ="")
    0.79
    ças
    0.79
     haline
    0.78
    یکٹر
    0.78
    ^{*
    0.78
     optio
    0.78
    ânia
    0.77
    POSITIVE LOGITS
     Coalition
    0.91
    കോ
    0.85
     Cobalt
    0.83
     Contour
    0.82
    izure
    0.81
     nc
    0.78
    흉
    0.75
    ാനുള്ള
    0.74
     incentive
    0.74
    지난
    0.74
    Activations Density 0.002%

    No Known Activations