© 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. 55640
    Prev
    Next
    INDEX
    Explanations

    out of, up to, back into

    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
     of
    -1.34
     nî
    -0.94
     overly
    -0.93
     strikingly
    -0.93
     تمامی
    -0.89
    _
    -0.89
     frequentemente
    -0.89
    ↵↵
    -0.87
    totally
    -0.86
    commonly
    -0.84
    POSITIVE LOGITS
     Putting
    1.12
    рія
    1.09
     Taking
    1.06
     Some
    1.02
     first
    1.02
     unrelenting
    1.00
    \|^{
    0.99
     Make
    0.98
     yourself
    0.97
     Making
    0.97
    Activations Density 0.044%

    No Known Activations