© 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. 92414
    Prev
    Next
    INDEX
    Explanations

    program exit

    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
     אי
    -0.72
    ους
    -0.69
     Freiw
    -0.69
    RET
    -0.68
    CROSSTALK
    -0.67
     manner
    -0.66
    graaf
    -0.66
     ден
    -0.65
    faces
    -0.65
     Merritt
    -0.65
    POSITIVE LOGITS
    ֶה
    0.74
    tfidf
    0.68
    SharedDtor
    0.67
    ְל
    0.66
     کمک
    0.66
    nginx
    0.66
    sas
    0.65
    DAI
    0.64
    Assembler
    0.64
    Reduced
    0.63
    Activations Density 0.045%

    No Known Activations