© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203016
    Prev
    Next
    INDEX
    Explanations

    lodging and accommodation names

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

    negative statements or comparisons

    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
    Not in Any Lists

    No Comments

    Negative Logits
     presentaciones
    0.50
     clínicos
    0.44
     mediana
    0.44
     infecciones
    0.42
     discapacidad
    0.42
     retrie
    0.42
     entornos
    0.42
    ㅃ
    0.41
     rád
    0.41
     интел
    0.40
    POSITIVE LOGITS
    lipper
    0.47
    ARIO
    0.46
    olg
    0.42
    örm
    0.40
     Οι
    0.40
    chai
    0.39
     Dyn
    0.38
    Foo
    0.38
     Foo
    0.38
    ildo
    0.38
    Activations Density 0.001%

    No Known Activations