© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5114
    Prev
    Next
    INDEX
    Explanations

    team at or of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
     [][]
    1.49
    PLATES
    1.46
     iterable
    1.46
    urunan
    1.45
    chakra
    1.44
     graduellement
    1.43
    ariyam
    1.43
    häuse
    1.42
    [][]
    1.40
    īg
    1.39
    POSITIVE LOGITS
     based
    1.51
     agreed
    1.50
     think
    1.45
     over
    1.39
     chez
    1.27
     thought
    1.27
     hos
    1.26
     running
    1.26
     above
    1.24
     feasibility
    1.24
    Activations Density 0.069%

    No Known Activations