© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43953
    Prev
    Next
    INDEX
    Explanations

    much of

    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_10/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
    栳
    -1.86
    even
    -1.77
    🫃
    -1.75
    
    -1.66
    sometimes
    -1.63
     you
    -1.63
    again
    -1.60
     participado
    -1.55
     easiest
    -1.51
     включая
    -1.49
    POSITIVE LOGITS
     of
    2.14
     After
    2.14
     When
    1.88
     Before
    1.63
     Chambres
    1.63
     menjel
    1.60
     During
    1.59
    ью
    1.58
     japonais
    1.57
     With
    1.56
    Activations Density 0.013%

    No Known Activations