© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16115
    Prev
    Next
    INDEX
    Explanations

    noisy measurements and data processing

    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_22/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
     muelle
    -1.04
     взгляд
    -1.02
    lccccc
    -0.97
     demostra
    -0.96
    anyakan
    -0.94
    хии
    -0.92
    LatLng
    -0.91
     öf
    -0.88
    鍬
    -0.87
    urally
    -0.85
    POSITIVE LOGITS
     receber
    1.11
     procedure
    1.09
    Noise
    1.02
     descobrir
    0.98
     raw
    0.98
     recording
    0.94
     technique
    0.93
     results
    0.93
     Procedure
    0.93
     erheben
    0.92
    Activations Density 0.145%

    No Known Activations