© 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. 34-GEMMASCOPE-RES-131K
    4. 59785
    Prev
    Next
    INDEX
    Explanations

    apple operating systems and devices

    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
    cribe
    -0.76
    ASUS
    -0.75
     सही
    -0.70
    fowl
    -0.69
     kontroli
    -0.69
    NOVEMBER
    -0.69
    jRadioButton
    -0.68
    蠕
    -0.68
    Elemental
    -0.68
    崇
    -0.67
    POSITIVE LOGITS
     OS
    0.85
    침
    0.82
     nunc
    0.82
    Aval
    0.79
     sdk
    0.74
    OS
    0.73
     pernyataan
    0.73
     SDK
    0.72
     tv
    0.71
    JpaRepository
    0.71
    Activations Density 0.078%

    No Known Activations