© 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. 16-GEMMASCOPE-2-RES-16K
    7. 416
    Prev
    Next
    INDEX
    Explanations

    2 and units

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

    2 followed by number

    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_16_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
     in
    1.16
     the
    1.05
     في
    0.77
    is
    0.76
    ↵
    0.73
    ;
    0.71
     auteur
    0.70
     ABV
    0.69
     is
    0.68
     attire
    0.66
    POSITIVE LOGITS
    い
    1.14
    ون
    0.93
    いを
    0.92
    t
    0.88
    た
    0.87
    на
    0.87
    다
    0.86
    য়
    0.86
    ла
    0.84
    いい
    0.83
    Activations Density 0.536%

    No Known Activations