© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14450
    Prev
    Next
    INDEX
    Explanations

    reminiscing about the past

    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
    又要
    -0.99
     certainly
    -0.93
    conhe
    -0.93
    
    -0.91
    kue
    -0.91
     Nachmittag
    -0.91
    龊
    -0.91
    なのですが
    -0.91
     Gegenstände
    -0.89
    TacToe
    -0.88
    POSITIVE LOGITS
    ?
    2.67
    ?"
    1.18
    ?”
    1.13
    Sometimes
    1.09
     Sometimes
    1.07
    MEDIATE
    1.01
    ؟
    0.98
     when
    0.97
     ゴルフ
    0.96
     Bruch
    0.94
    Activations Density 0.016%

    No Known Activations