© 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. 183261
    Prev
    Next
    INDEX
    Explanations

    surrounded by, sports athletes, favorite coffee

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

    expresses a state or feeling

    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
     coulomb
    0.59
     dirigés
    0.55
     maî
    0.53
     সময়ই
    0.52
     proposé
    0.52
     demora
    0.51
     deuxième
    0.50
    쾺
    0.50
    রোধ
    0.49
     rougeâtres
    0.49
    POSITIVE LOGITS
    ện
    0.46
    institut
    0.45
    jd
    0.45
    athan
    0.44
    i
    0.43
    ط
    0.42
    liament
    0.42
    بان
    0.42
     DR
    0.41
     MODEL
    0.41
    Activations Density 0.001%

    No Known Activations