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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38675
    Prev
    Next
    INDEX
    Explanations

    locations and states of being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     here
    -1.18
    事は
    -1.13
     of
    -1.09
     hierfür
    -1.04
     inscripción
    -0.99
    ᔪ
    -0.99
     powerfully
    -0.98
     wherever
    -0.96
    持って
    -0.95
     continually
    -0.94
    POSITIVE LOGITS
     most
    1.00
     after
    0.98
     before
    0.97
     when
    0.97
    bof
    0.96
    ≧
    0.92
    dienne
    0.91
     शुर
    0.88
    ≦
    0.88
    úrese
    0.86
    Activations Density 0.057%

    No Known Activations