© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62983
    Prev
    Next
    INDEX
    Explanations

    adjective followed by 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_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
     prípade
    -1.09
     recupero
    -1.07
     čier
    -0.97
     intended
    -0.96
     increasing
    -0.95
     véritable
    -0.94
    はこちらから
    -0.93
     кнопку
    -0.92
    上げた
    -0.92
     sni
    -0.91
    POSITIVE LOGITS
     staff
    1.53
     service
    1.29
     hostel
    1.16
    Staff
    1.15
    staff
    1.13
     staffs
    1.11
    structors
    1.11
    ))\
    1.03
    SERVICE
    1.02
     facilities
    1.00
    Activations Density 0.032%

    No Known Activations