© 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. 153249
    Prev
    Next
    INDEX
    Explanations

    electrical engineeringColbycontractorsautomaticmining equipmentapplesaucebad guyscelullitemoviefinancial

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

    ChatGPT Plus API

    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
     カー
    0.47
    ミ
    0.44
    м
    0.44
     f
    0.43
     meine
    0.42
     eukaryotic
    0.42
    1
    0.42
     мое
    0.41
     binge
    0.40
     把
    0.40
    POSITIVE LOGITS
     aidant
    0.57
    rét
    0.54
     الدین
    0.50
     شہادت
    0.49
     حقیقت
    0.49
     próprios
    0.49
    lors
    0.48
     environnement
    0.47
    وسیع
    0.47
     propio
    0.47
    Activations Density 0.001%

    No Known Activations