© 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. 34-GEMMASCOPE-RES-131K
    7. 107115
    Prev
    Next
    INDEX
    Explanations

    curly bracket or Africa locations

    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
     created
    -0.85
     unique
    -0.84
    之色
    -0.82
     create
    -0.82
    يوب
    -0.81
    主
    -0.81
    acamata
    -0.78
     efficient
    -0.77
     genoemd
    -0.76
     pdf
    -0.75
    POSITIVE LOGITS
    ッキー
    0.85
     VERY
    0.85
     delightfully
    0.85
    frequently
    0.84
    ⊛
    0.83
     kellett
    0.82
    Beruf
    0.82
    Tils
    0.81
     например
    0.81
    Scalars
    0.80
    Activations Density 0.004%

    No Known Activations