© 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. 205292
    Prev
    Next
    INDEX
    Explanations

    context about building

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

    AI research and applications

    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
    Emojis
    0.51
    muş
    0.51
    يكون
    0.50
    Alumno
    0.49
    懑
    0.49
    Sementara
    0.49
    istische
    0.47
    ધો
    0.47
    섰
    0.47
    시다
    0.47
    POSITIVE LOGITS
     strategies
    0.59
     path
    0.56
     I
    0.55
     actuators
    0.55
     embodiment
    0.55
     beam
    0.54
     hydraulic
    0.54
     elution
    0.53
     heterogeneity
    0.53
     renovation
    0.52
    Activations Density 0.000%

    No Known Activations