© 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. 34-GEMMASCOPE-RES-131K
    4. 49868
    Prev
    Next
    INDEX
    Explanations

    text wrap and line break

    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
    RITION
    -0.83
     cordones
    -0.79
    ież
    -0.77
    Jîn
    -0.77
    UIControlState
    -0.75
    štění
    -0.75
    DNEY
    -0.75
    setIcon
    -0.75
     frequência
    -0.74
    Correction
    -0.73
    POSITIVE LOGITS
     wrap
    2.19
    wrap
    2.05
     break
    1.91
     Wrap
    1.82
    break
    1.78
     wraps
    1.74
     wrapping
    1.72
    Wrap
    1.69
     breaks
    1.64
     breaking
    1.63
    Activations Density 0.088%

    No Known Activations