© 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. 142624
    Prev
    Next
    INDEX
    Explanations

    heart space

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

    short straightforward interaction content

    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
    )
    0.49
     ۸
    0.47
     ۲
    0.45
    )%
    0.45
     ۵
    0.45
     %)
    0.44
     Breaking
    0.44
     Colour
    0.44
    ۵
    0.43
     Banks
    0.43
    POSITIVE LOGITS
    顧問
    0.44
    несе
    0.44
     mussten
    0.44
    和大
    0.44
    स्तिक
    0.43
     inlets
    0.43
     zh
    0.43
     covariates
    0.43
    和社会
    0.43
    technical
    0.42
    Activations Density 0.000%

    No Known Activations