© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38384
    Prev
    Next
    INDEX
    Explanations

    guide and tutorial

    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
     konserv
    -1.59
     protokol
    -1.55
     lü
    -1.53
     rü
    -1.51
     настолько
    -1.50
    '
    -1.50
     kalender
    -1.44
     klassi
    -1.44
     Kristus
    -1.43
     visse
    -1.43
    POSITIVE LOGITS
     including
    1.55
     now
    1.52
     with
    1.48
     using
    1.47
     at
    1.45
     on
    1.45
     and
    1.41
    ﾈ
    1.39
     featuring
    1.38
     行っ
    1.38
    Activations Density 0.028%

    No Known Activations