© 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. 34-GEMMASCOPE-RES-131K
    4. 118498
    Prev
    Next
    INDEX
    Explanations

    formal text, URLs, symbols

    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_34/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
    Despite
    -1.73
    With
    -1.72
    While
    -1.67
    Since
    -1.64
    Although
    -1.60
    ・・
    -1.59
     at
    -1.59
    Both
    -1.59
     for
    -1.57
    Because
    -1.55
    POSITIVE LOGITS
     Grüßen
    1.43
    菒
    1.40
     Saltar
    1.35
    耵
    1.32
     amazingly
    1.32
     spearheaded
    1.30
    戗
    1.30
     hugely
    1.30
    conte
    1.28
    ]
    1.28
    Activations Density 0.004%

    No Known Activations