© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5765
    Prev
    Next
    INDEX
    Explanations

    concessions, contrasts, or acknowledgements

    np_acts-logits-general · gemini-2.5-flash-lite

    contrast words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_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
    ，
    1.15
    ،
    1.13
    ,
    1.02
    *,
    0.98
     ，
    0.93
     ،
    0.92
     ,
    0.91
    !,
    0.89
    ,,
    0.84
    $,
    0.82
    POSITIVE LOGITS
     although
    1.16
     aunque
    0.93
     albeit
    0.93
     obwohl
    0.82
    although
    0.77
     protože
    0.73
     choć
    0.73
     несмотря
    0.73
     iako
    0.72
    albeit
    0.71
    Activations Density 0.229%

    No Known Activations