© 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. 26164
    Prev
    Next
    INDEX
    Explanations

    retrospectively understand adjusted took place follow make sense

    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
    报记者
    -1.16
     Θε
    -1.12
    Eliminar
    -1.02
    モノ
    -1.01
     Jego
    -1.00
    这一点
    -0.99
    ১
    -0.98
    Enllaces
    -0.97
     weißem
    -0.96
     Δια
    -0.96
    POSITIVE LOGITS
     will
    1.23
     pueden
    1.12
     melalui
    1.11
     varied
    1.00
     dubbio
    0.96
    但是
    0.95
     olika
    0.95
     spettacolo
    0.95
     porque
    0.94
     дает
    0.94
    Activations Density 0.089%

    No Known Activations