© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 16602
    Prev
    Next
    INDEX
    Explanations

    here followed by punctuation

    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_65k_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
    ۰
    0.78
     ceram
    0.66
    is
    0.64
    as
    0.62
     spez
    0.62
     Cea
    0.62
     arqué
    0.61
    érence
    0.61
    ון
    0.60
    é
    0.60
    POSITIVE LOGITS
    abouts
    0.96
     in
    0.86
    на
    0.80
    ifrån
    0.76
    ла
    0.74
    1
    0.74
    fordshire
    0.70
    ال
    0.69
    ли
    0.65
    在
    0.63
    Activations Density 0.029%

    No Known Activations