© 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. 75438
    Prev
    Next
    INDEX
    Explanations

    supporting, diagnostic, control, reference

    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
     thẳng
    -0.90
     abrupt
    -0.90
    redirectTo
    -0.87
     refreshed
    -0.85
     renewed
    -0.83
    Confirmed
    -0.82
    ȃ
    -0.82
    嫑
    -0.81
     grin
    -0.81
    
    -0.81
    POSITIVE LOGITS
     introductory
    1.00
     promotional
    0.98
     control
    0.95
     explanatory
    0.89
     diagnostic
    0.88
     auxiliary
    0.88
     reference
    0.85
     Introductory
    0.84
     опор
    0.84
     interpretive
    0.82
    Activations Density 0.288%

    No Known Activations