© 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. 4729
    Prev
    Next
    INDEX
    Explanations

    support and understanding

    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
    angun
    1.95
     appartiennent
    1.77
    setEnabled
    1.73
     kulturn
    1.70
    儡
    1.67
     appartient
    1.65
    ếng
    1.65
    隸
    1.62
    elift
    1.61
    عيب
    1.60
    POSITIVE LOGITS
    through
    1.53
     through
    1.53
     throughout
    1.49
     ensuring
    1.47
     verso
    1.45
     thru
    1.44
     via
    1.38
     during
    1.34
     ώστε
    1.30
    mming
    1.29
    Activations Density 0.057%

    No Known Activations