© 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. 164428
    Prev
    Next
    INDEX
    Explanations

    live music and show

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

    connecting items and social compatibility

    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
     手
    0.54
     Annotation
    0.46
     auront
    0.46
     \}
    0.45
    TRANSFER
    0.43
    WHITE
    0.42
    interpolate
    0.42
     inflater
    0.41
     Azure
    0.41
    পুণ
    0.41
    POSITIVE LOGITS
    érés
    0.48
    .([]
    0.47
    тором
    0.45
    çada
    0.44
    élix
    0.44
    ез
    0.43
    כי
    0.43
    StaffID
    0.43
    plexity
    0.43
     ఒకటి
    0.42
    Activations Density 0.001%

    No Known Activations