© 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. 90583
    Prev
    Next
    INDEX
    Explanations

    fileID: followed by colon

    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
     Mauricio
    -0.73
     センター
    -0.71
    obenzene
    -0.69
    짐
    -0.69
     Hawk
    -0.66
    곁
    -0.65
    
    -0.65
    POINTER
    -0.64
    缓
    -0.64
    🐎
    -0.64
    POSITIVE LOGITS
     prosthesis
    0.74
     Indul
    0.70
    SPECIFIED
    0.67
     Inse
    0.67
     Submissions
    0.65
    IGENCE
    0.65
     Kork
    0.65
     Hiller
    0.64
     showing
    0.64
    atomy
    0.63
    Activations Density 0.113%

    No Known Activations