© 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. 1745
    Prev
    Next
    INDEX
    Explanations

    type casting and consumption

    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
     Zona
    1.64
     Z
    1.52
     Excellence
    1.50
     O
    1.50
     Fecha
    1.46
     Hits
    1.45
     Análisis
    1.44
     L
    1.44
     Fax
    1.44
     …
    1.43
    POSITIVE LOGITS
    hose
    1.49
     governed
    1.47
     ascribed
    1.47
     signified
    1.47
    sometimes
    1.46
     fostered
    1.43
     subjug
    1.41
     metaphor
    1.41
    inducing
    1.39
     engender
    1.36
    Activations Density 0.301%

    No Known Activations