© 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. 75129
    Prev
    Next
    INDEX
    Explanations

    return type

    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
    就不
    -0.88
     зрения
    -0.86
    −/−
    -0.85
    霎
    -0.85
    äki
    -0.83
     Deixe
    -0.82
    )}
    -0.82
     Get
    -0.80
    deserved
    -0.78
    Kjelder
    -0.77
    POSITIVE LOGITS
    CTIONS
    1.09
    VALUES
    1.04
     hei
    0.93
    뺀
    0.91
     reCAPTCHA
    0.90
    IDENCE
    0.90
    虓
    0.90
     mey
    0.88
    鯨
    0.88
    ımıza
    0.88
    Activations Density 0.004%

    No Known Activations