© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 691
    Prev
    Next
    INDEX
    Explanations

    names with M initial

    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
    Negative Logits
    ak
    1.80
    are
    1.63
    '
    1.55
    in
    1.49
    p
    1.44
    itt
    1.39
    uk
    1.34
    oh
    1.30
    am
    1.29
    IN
    1.29
    POSITIVE LOGITS
    ו
    1.40
    ;
    1.25
    ри
    1.18
    ],
    1.16
    t
    1.15
    }
    1.14
    تها
    1.12
     pajama
    1.07
    くちゃ
    1.06
    त
    1.06
    Activations Density 4.134%

    No Known Activations