© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3806
    Prev
    Next
    INDEX
    Explanations

    access, create, grant, read, run

    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
    !
    0.87
    Artwork
    0.87
    stelling
    0.86
    Trait
    0.85
    èt
    0.84
    겠다는
    0.82
     dimiliki
    0.81
    %.
    0.80
    infused
    0.80
    Foster
    0.80
    POSITIVE LOGITS
     Norton
    1.37
     telef
    1.34
     oracle
    1.33
     Buffett
    1.32
     Sears
    1.31
     MCC
    1.31
     TAL
    1.31
     INFO
    1.30
     REPLY
    1.27
     COR
    1.27
    Activations Density 0.113%

    No Known Activations