© 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. 90801
    Prev
    Next
    INDEX
    Explanations

    details

    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
     faſt
    -2.69
    },
    -2.61
     помогает
    -2.41
    銠
    -2.41
    ,
    -2.30
    $,
    -2.28
    𝐭
    -2.25
    <i>
    -2.25
    )));
    -2.23
    ',
    -2.22
    POSITIVE LOGITS
    During
    2.38
    趼
    2.38
    觧
    2.34
     details
    2.31
    
    2.31
    ◳
    2.27
    detalles
    2.25
    謬
    2.23
    ஂ
    2.22
    Even
    2.17
    Activations Density 0.010%

    No Known Activations