© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92297
    Prev
    Next
    INDEX
    Explanations

    door and its parts

    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
    리아
    -1.02
     überprü
    -1.01
     tiefen
    -0.94
    垰
    -0.93
    ativistic
    -0.91
    ětí
    -0.91
     richtigen
    -0.89
    garia
    -0.88
     montagnes
    -0.88
     inneren
    -0.87
    POSITIVE LOGITS
    🚪
    1.81
    teps
    0.98
    frame
    0.97
     COUNTY
    0.97
     knob
    0.89
    を入
    0.86
     latch
    0.86
     colectiva
    0.86
     Aguas
    0.86
     Depending
    0.85
    Activations Density 0.012%

    No Known Activations