© 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. 34-GEMMASCOPE-RES-131K
    7. 115718
    Prev
    Next
    INDEX
    Explanations

    panel B or number

    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
     klassi
    -0.83
     شیشه
    -0.80
    ссий
    -0.79
    ]_{\
    -0.78
     username
    -0.76
    propTypes
    -0.75
    writeByte
    -0.75
     உ
    -0.75
    Skocz
    -0.73
    ntomas
    -0.73
    POSITIVE LOGITS
     panels
    4.63
     panel
    4.59
     Panel
    3.86
    panel
    3.80
    Panel
    3.69
     Panels
    3.66
    Panels
    3.64
    panels
    3.48
     PANEL
    3.31
    PANEL
    2.91
    Activations Density 0.045%

    No Known Activations