© 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. 118049
    Prev
    Next
    INDEX
    Explanations

    practice high, clarifies that, love thee

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

    cash pooling, miles further

    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
     数字
    0.47
     créditos
    0.45
     ApiException
    0.44
     discredited
    0.43
    бал
    0.43
    এশিয়া
    0.43
    6
    0.42
     éc
    0.42
    *((
    0.42
     Há
    0.42
    POSITIVE LOGITS
     olefin
    0.50
    koľ
    0.50
    ྫ
    0.47
    壘
    0.44
     Bernoulli
    0.44
    berto
    0.43
    erar
    0.42
     televisi
    0.42
    盹
    0.42
    ॉर्ड
    0.42
    Activations Density 0.000%

    No Known Activations