© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119965
    Prev
    Next
    INDEX
    Explanations

    names beginning with Mac, Le, Ru, Gu

    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_10/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
    䜣
    -3.03
    ৄ
    -2.53
     ancianos
    -2.48
    ፁ
    -2.45
    𖤍
    -2.42
    
    -2.39
    罴
    -2.39
    
    -2.38
    </h2>
    -2.27
    饧
    -2.27
    POSITIVE LOGITS
    When
    4.03
    If
    3.97
    You
    3.72
    What
    3.50
    It
    3.28
    There
    3.25
    >
    3.25
    ization
    3.22
    From
    3.19
    ’
    3.19
    Activations Density 0.184%

    No Known Activations