© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68328
    Prev
    Next
    INDEX
    Explanations

    because or otherwise

    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_22/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
     ekonomi
    -0.99
     spann
    -0.87
     interieur
    -0.86
    heren
    -0.85
     unheard
    -0.85
    sekten
    -0.85
     ministres
    -0.82
     serre
    -0.82
    asks
    -0.81
    Zodiac
    -0.81
    POSITIVE LOGITS
     lest
    1.42
     otherwise
    1.11
    以免
    1.09
     preserve
    1.06
     Gefahr
    1.02
     tránh
    1.02
     иначе
    1.01
     sonst
    1.01
     because
    0.98
     Otherwise
    0.96
    Activations Density 0.039%

    No Known Activations