© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 273
    Prev
    Next
    INDEX
    Explanations

    in common or together

    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
     róż
    -0.82
     desigual
    -0.82
    ilions
    -0.80
     overwrite
    -0.79
    Respectfully
    -0.79
    vore
    -0.78
    opter
    -0.77
    entennial
    -0.76
    chial
    -0.75
    vah
    -0.74
    POSITIVE LOGITS
     together
    1.55
     cùng
    1.54
    共同
    1.53
    一起
    1.46
     mutually
    1.45
     both
    1.41
     mutual
    1.41
    Both
    1.32
     gemeinsam
    1.30
    together
    1.27
    Activations Density 0.051%

    No Known Activations