© 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. 31-GEMMASCOPE-2-RES-262K
    7. 43185
    Prev
    Next
    INDEX
    Explanations

    the, one, waves, to, U, as, has, of

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

    rim lighting

    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_31_width_262k_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
     tcpHeader
    0.53
     রাম
    0.51
     божомолу
    0.50
     બના
    0.50
    ‌پ
    0.49
    Manisha
    0.48
    畚
    0.48
     बनाने
    0.47
     पण
    0.47
    Mush
    0.47
    POSITIVE LOGITS
    odom
    0.45
    ا
    0.44
    epsilon
    0.43
    ային
    0.43
     algorithms
    0.42
     desempeño
    0.42
     administrador
    0.42
    মতো
    0.42
    li
    0.42
    ǎo
    0.41
    Activations Density 0.000%

    No Known Activations