© 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. 30370
    Prev
    Next
    INDEX
    Explanations

    falling, declining, deteriorating

    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
    mentaires
    -0.94
    WillAppear
    -0.90
     ویکی‌آمباردا
    -0.86
     thắng
    -0.86
     masih
    -0.84
     hesit
    -0.82
     каранда
    -0.82
    ++];
    -0.81
    reur
    -0.81
    意外
    -0.81
    POSITIVE LOGITS
     downhill
    2.88
     decline
    2.75
     deterioration
    2.31
     deteriorate
    2.19
     downward
    2.11
     Decline
    2.09
     decay
    1.98
     slide
    1.97
     declining
    1.97
    decline
    1.90
    Activations Density 0.067%

    No Known Activations