© 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. 33897
    Prev
    Next
    INDEX
    Explanations

    listing items with commas

    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
    為に
    -1.61
    菒
    -1.59
    andis
    -1.53
    ఝ
    -1.53
    ਗ਼
    -1.50
    ほら
    -1.45
     zoude
    -1.44
    
    -1.42
     montrer
    -1.41
     család
    -1.41
    POSITIVE LOGITS
     and
    3.13
     including
    2.09
     if
    2.05
     or
    1.88
     as
    1.86
     which
    1.82
     now
    1.73
     all
    1.63
     during
    1.63
     although
    1.61
    Activations Density 0.072%

    No Known Activations