© 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. 86139
    Prev
    Next
    INDEX
    Explanations

    magical lights

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

    lights and gardens

    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
     Uncertainty
    0.44
     Sunglasses
    0.43
     Crime
    0.42
     Emergency
    0.40
     mediator
    0.38
     Neighbourhood
    0.38
     პ
    0.38
    InsertInt
    0.38
     indetermin
    0.37
    ᱼ
    0.37
    POSITIVE LOGITS
    বস্ত
    0.42
    navigate
    0.42
     artistry
    0.41
    SEQU
    0.41
    寒
    0.40
    🍁
    0.40
    transformed
    0.39
     carve
    0.39
    someone
    0.39
    grade
    0.39
    Activations Density 0.094%

    No Known Activations