© 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. 75016
    Prev
    Next
    INDEX
    Explanations

    negative outcomes occurring

    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
    hdysval
    -1.05
    sidian
    -1.05
     Brabant
    -1.01
     OFFER
    -1.00
     веке
    -0.99
    Œuvres
    -0.99
     falta
    -0.98
    ]));
    -0.97
     forn
    -0.97
    האם
    -0.96
    POSITIVE LOGITS
     caused
    1.33
     occurred
    1.26
     occurs
    1.23
     can
    1.16
    0
    1.13
    tonsoft
    1.11
     occur
    1.10
     in
    1.10
     treści
    1.08
     problemática
    1.08
    Activations Density 0.112%

    No Known Activations