© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 15570
    Prev
    Next
    INDEX
    Explanations

    questions and titles

    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_22/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
     while
    -1.70
     or
    -1.55
     While
    -1.52
     and
    -1.52
     During
    -1.49
    為に
    -1.49
     this
    -1.42
     sizable
    -1.40
     With
    -1.30
     noteworthy
    -1.27
    POSITIVE LOGITS
    は
    2.00
    がある
    1.99
    が
    1.91
    を
    1.80
    も
    1.73
    もしか
    1.59
    と
    1.59
    だろうか
    1.55
    まさに
    1.52
    など
    1.51
    Activations Density 0.010%

    No Known Activations