© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40451
    Prev
    Next
    INDEX
    Explanations

    showed that

    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_10/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
    e
    -3.84
    u
    -2.98
    er
    -2.84
     尔
    -2.77
     if
    -2.59
    ৹
    -2.55
    tividade
    -2.47
    ampaikan
    -2.44
    ৪
    -2.38
    他的
    -2.34
    POSITIVE LOGITS
     anteriormente
    2.66
    واسطة
    2.55
    色が
    2.53
    乆
    2.53
     Praw
    2.48
    стреча
    2.47
     COULD
    2.47
    
    2.44
     δεν
    2.42
     Their
    2.41
    Activations Density 0.010%

    No Known Activations