© 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. 62975
    Prev
    Next
    INDEX
    Explanations

    newspaper names

    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
     kế
    -0.71
     h
    -0.70
    umán
    -0.68
    凄い
    -0.68
     unloaded
    -0.67
    Fluorescence
    -0.66
     πρόσ
    -0.66
     beru
    -0.66
     Corte
    -0.65
    看你
    -0.65
    POSITIVE LOGITS
     newspaper
    1.13
     skues
    1.07
     Herald
    1.02
    zeiger
    0.99
     Dispatch
    0.99
     Journal
    0.91
     news
    0.87
     Telegram
    0.85
     Sentinel
    0.85
    Star
    0.84
    Activations Density 0.042%

    No Known Activations