© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38152
    Prev
    Next
    INDEX
    Explanations

    starts of common phrases

    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
    γρά
    -0.93
    戦争
    -0.81
     gwia
    -0.78
    っていると
    -0.77
     professeurs
    -0.75
    כום
    -0.74
     gorą
    -0.74
    hatikan
    -0.74
    Zee
    -0.73
     libéral
    -0.73
    POSITIVE LOGITS
     EVP
    0.87
    CallBack
    0.87
    Bounding
    0.83
    ismen
    0.81
    ⊂
    0.79
    BindingResult
    0.78
    Rw
    0.78
    leit
    0.77
    strans
    0.75
     semble
    0.74
    Activations Density 0.004%

    No Known Activations