© 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. 36573
    Prev
    Next
    INDEX
    Explanations

    URL parameters and identifiers

    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
     étan
    -1.02
     suspensão
    -0.99
    chris
    -0.98
     来自
    -0.96
    强者
    -0.94
     problemy
    -0.92
     óleo
    -0.91
     moze
    -0.90
     角色
    -0.90
     unbearable
    -0.90
    POSITIVE LOGITS
    Eles
    0.99
    Они
    0.92
     identifiers
    0.91
    BASEPATH
    0.90
    ATORY
    0.90
    ()?;
    0.89
     identifies
    0.89
    ând
    0.89
     Eles
    0.88
    ürlich
    0.88
    Activations Density 0.005%

    No Known Activations