© 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. 216099
    Prev
    Next
    INDEX
    Explanations

    location or direction

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

    chemical compounds, biological actions, or conditions

    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
    Negative Logits
    0.55
    THE
    0.50
    APS
    0.48
    Sequ
    0.46
    CEO
    0.46
    Really
    0.46
    very
    0.45
    数の
    0.45
    -
    0.44
    have
    0.44
    POSITIVE LOGITS
    íj
    0.55
     univerz
    0.54
     Մ
    0.50
     Encu
    0.49
     Är
    0.48
     rövid
    0.47
     մ
    0.47
     Nicht
    0.46
     ට
    0.46
     သ
    0.46
    Activations Density 0.000%

    No Known Activations