© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14149
    Prev
    Next
    INDEX
    Explanations

    greeting or acknowledgment

    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_13_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
    Ꮰ
    1.26
     preservar
    1.21
    <unused910>
    1.20
     discutir
    1.18
     limpar
    1.17
     montar
    1.15
    妘
    1.15
     ඇත
    1.15
     produzir
    1.13
     setSnackbar
    1.13
    POSITIVE LOGITS
     which
    2.45
     that
    2.33
     whose
    2.32
     who
    2.23
    which
    2.22
    that
    2.11
     которые
    2.03
    whose
    2.02
    who
    1.99
     whom
    1.97
    Activations Density 0.208%

    No Known Activations