© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1069
    Prev
    Next
    INDEX
    Explanations

    adjective of significance

    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_65k_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
     and
    2.44
    The
    2.28
     a
    2.25
     the
    2.24
    <0xF3>
    2.18
     to
    2.17
     The
    2.12
     is
    2.12
     It
    2.10
     и
    2.06
    POSITIVE LOGITS
    egir
    1.86
     respectable
    1.72
     gigantic
    1.69
     powerful
    1.69
     hugely
    1.68
     mighty
    1.68
     ridiculously
    1.65
     dreadful
    1.64
     hideous
    1.64
     monstrous
    1.63
    Activations Density 1.792%

    No Known Activations