© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12369
    Prev
    Next
    INDEX
    Explanations

    crafting content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     truly
    1.74
     blows
    1.59
     really
    1.49
     oppressed
    1.49
    och
    1.48
     might
    1.48
    ucking
    1.47
    겔
    1.47
     blew
    1.47
     suddenly
    1.44
    POSITIVE LOGITS
    Labeled
    2.01
     informazioni
    2.00
     défin
    1.99
     significato
    1.99
     conformément
    1.98
    湪
    1.98
    TextureAsset
    1.97
     semestre
    1.97
     caratteristiche
    1.97
     Sereth
    1.96
    Activations Density 0.100%

    No Known Activations