© 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. 118774
    Prev
    Next
    INDEX
    Explanations

    prove that or whether

    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
    ……」
    -1.71
    。」
    -1.65
     словно
    -1.63
    ?」
    -1.54
     tantas
    -1.54
     двумя
    -1.52
    ſie
    -1.52
    鷺
    -1.52
     \"
    -1.48
    ldorf
    -1.47
    POSITIVE LOGITS
    2
    2.05
    ilight
    1.70
    AT
    1.69
    viro
    1.64
     ausein
    1.61
    泐
    1.57
     reiter
    1.56
    Again
    1.56
    ところは
    1.56
     女の子
    1.55
    Activations Density 0.023%

    No Known Activations