© 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. 108378
    Prev
    Next
    INDEX
    Explanations

    HTML tags and markup

    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
     so
    -1.01
     just
    -0.99
     which
    -0.97
     one
    -0.96
     get
    -0.96
     in
    -0.90
     confident
    -0.90
    ÓW
    -0.85
     information
    -0.84
     this
    -0.84
    POSITIVE LOGITS
    </b>
    1.10
    都已经
    1.05
    quoted
    1.02
    きれいな
    1.02
    从来没有
    0.96
    __':
    0.96
    </strong>
    0.94
     réussi
    0.94
     réussir
    0.93
    帮你
    0.92
    Activations Density 0.004%

    No Known Activations