© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 100767
    Prev
    Next
    INDEX
    Explanations

    birth certificates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
    gal
    0.40
    Maf
    0.39
    Casc
    0.38
     rodzaj
    0.36
     saj
    0.36
    𝒈
    0.36
    avanja
    0.35
     accusantium
    0.35
    brock
    0.35
    approach
    0.35
    POSITIVE LOGITS
     Transport
    0.42
     Banana
    0.41
     откло
    0.40
     Bishop
    0.40
     Esp
    0.38
     nourrice
    0.37
     Admission
    0.36
     removeItem
    0.36
    丹
    0.36
     Invest
    0.36
    Activations Density 0.000%

    No Known Activations