© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 138172
    Prev
    Next
    INDEX
    Explanations

    magnitude of scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä
    1.06
    isas
    1.01
    aru
    0.96
    ot
    0.93
    othe
    0.93
    ervice
    0.92
    ethe
    0.91
    ost
    0.91
    ollen
    0.89
    otional
    0.88
    POSITIVE LOGITS
     przesz
    1.17
     powied
    1.09
    )];
    1.07
     aument
    1.02
     poziom
    1.02
    G
    1.01
     prodotti
    1.00
    அ
    1.00
    アメリカ
    0.98
    )};
    0.98
    Activations Density 0.001%

    No Known Activations