© 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. 22-GEMMASCOPE-RES-131K
    7. 16151
    Prev
    Next
    INDEX
    Explanations

    looking for

    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
     when
    -1.34
     their
    -1.16
     כשה
    -1.14
     whenever
    -1.13
     everything
    -1.12
     cuando
    -1.11
     everyone
    -1.09
     every
    -1.08
    Lorsque
    -1.08
    IANGLES
    -1.05
    POSITIVE LOGITS
     or
    1.31
     of
    1.29
     your
    1.13
     '=',
    1.10
     thì
    1.09
    château
    1.08
     about
    1.06
     for
    1.05
     yourself
    1.02
     yağı
    1.02
    Activations Density 0.029%

    No Known Activations