© 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. 69095
    Prev
    Next
    INDEX
    Explanations

    Q: followed by markup

    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
     its
    -1.37
     from
    -1.21
    ]),
    
    -1.18
     gangen
    -1.16
    場所に
    -1.15
     found
    -1.09
    襖
    -1.09
     wzglę
    -1.05
    НИК
    -1.05
    ěž
    -1.05
    POSITIVE LOGITS
    nappropriate
    1.08
    ebly
    1.08
    などを
    1.01
    banez
    1.00
    believe
    0.96
     véritable
    0.94
    Claro
    0.93
    igth
    0.93
    küche
    0.91
    blumen
    0.91
    Activations Density 0.000%

    No Known Activations