© 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. 187010
    Prev
    Next
    INDEX
    Explanations

    specifying alternatives, requirements, destinations

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

    describing methods and concepts

    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
     Vigo
    0.45
    FloatField
    0.45
    ອາ
    0.43
    नई
    0.42
    Felix
    0.42
    BDT
    0.42
    这是一个
    0.41
     febrero
    0.41
    呿
    0.41
     фами
    0.41
    POSITIVE LOGITS
     Anwendung
    0.54
     theolog
    0.51
    应用的
    0.48
     therapeutics
    0.46
    wendung
    0.46
    wendungs
    0.45
     therap
    0.45
     throng
    0.45
     Doctors
    0.45
     Heterocycl
    0.45
    Activations Density 0.000%

    No Known Activations