© 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. 31-GEMMASCOPE-2-RES-262K
    7. 43945
    Prev
    Next
    INDEX
    Explanations

    statistics, parasites, store, weights

    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/layer_31_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
     አንዳንድ
    0.56
     አንድ
    0.46
    inputSelect
    0.45
    kező
    0.45
    𝒌
    0.45
    ensureEqual
    0.45
     そ
    0.44
    ਭ
    0.43
    ající
    0.42
    kowe
    0.42
    POSITIVE LOGITS
     for
    0.53
     from
    0.51
     aggrieved
    0.51
     blame
    0.48
     crimes
    0.48
     epidemiology
    0.47
     blames
    0.46
     contamination
    0.44
     tariff
    0.44
     culp
    0.44
    Activations Density 0.009%

    No Known Activations