© 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. 128570
    Prev
    Next
    INDEX
    Explanations

    heard of names

    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
     ventana
    -1.05
    出生
    -1.00
    >
    -1.00
     columna
    -0.98
    observed
    -0.97
    мур
    -0.97
    眷
    -0.96
    Ł
    -0.95
     besonders
    -0.94
     observa
    -0.93
    POSITIVE LOGITS
     name
    1.88
     names
    1.53
    を知
    1.37
     familiarity
    1.35
     Names
    1.34
     Name
    1.27
    只是一个
    1.27
     know
    1.23
    Name
    1.22
     getName
    1.22
    Activations Density 0.057%

    No Known Activations