© 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. 122236
    Prev
    Next
    INDEX
    Explanations

    movements, update these, numbers, boat

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

    Kubernetes and age

    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
    ythe
    0.50
    ncbi
    0.48
    africa
    0.46
     الاست
    0.46
    柢
    0.46
     समुच्चय
    0.45
    㤟
    0.44
    പ്പെട്ട
    0.43
    in
    0.43
    QUES
    0.43
    POSITIVE LOGITS
     I
    0.52
     noter
    0.48
     싶
    0.45
     HomePage
    0.44
    It
    0.44
    싶
    0.43
    イヤ
    0.42
     manager
    0.42
    շ
    0.42
     not
    0.42
    Activations Density 0.001%

    No Known Activations