© 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. 10-GEMMASCOPE-RES-131K
    7. 101596
    Prev
    Next
    INDEX
    Explanations

    "A" followed by colon or descriptive noun

    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
    1
    -2.25
     this
    -2.00
     so
    -1.92
     occasionally
    -1.82
     markedly
    -1.79
     relentlessly
    -1.79
     noticeably
    -1.73
     blatantly
    -1.69
     undeniably
    -1.69
     ostensibly
    -1.69
    POSITIVE LOGITS
     saveurs
    1.66
    水泥
    1.63
    normally
    1.61
    烀
    1.60
     ungkap
    1.60
     instill
    1.60
    ✟
    1.58
    seems
    1.57
    within
    1.55
    㩒
    1.53
    Activations Density 0.025%

    No Known Activations