© 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. 10-GEMMASCOPE-RES-131K
    4. 90460
    Prev
    Next
    INDEX
    Explanations

    facts about information

    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
    
    -2.16
    <i>
    -2.13
    </h1>
    -1.71
    dzić
    -1.67
     locura
    -1.66
    copg
    -1.65
    </i>
    -1.63
    ynb
    -1.62
     acepción
    -1.59
    liwości
    -1.59
    POSITIVE LOGITS
    ፑ
    2.38
    0
    2.28
    2
    2.02
    𓆉
    2.02
    .
    1.96
    and
    1.89
    </em>
    1.88
    んだけど
    1.87
    鮃
    1.82
    lon
    1.77
    Activations Density 0.012%

    No Known Activations