© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 107813
    Prev
    Next
    INDEX
    Explanations

    topics concerning practical knowledge

    np_acts-logits-general · gemini-2.5-flash-lite

    contrasting tone and style

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    י
    0.55
    ي
    0.51
    ف
    0.50
    θε
    0.46
    語
    0.46
    уз
    0.45
    你看
    0.45
    س
    0.44
    ुरा
    0.44
    奈川
    0.43
    POSITIVE LOGITS
    prob
    0.55
    :
    0.53
    hound
    0.52
     postcards
    0.48
     Bungal
    0.48
     Collabor
    0.46
     Jurassic
    0.44
    ología
    0.44
     পুরাতন
    0.43
     instincts
    0.43
    Activations Density 0.001%

    No Known Activations