© 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. 73041
    Prev
    Next
    INDEX
    Explanations

    opening parenthesis `(`

    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
    当地
    -1.13
     first
    -1.06
     has
    -1.05
     because
    -1.05
     ostensibly
    -1.02
    、、
    -1.02
    首先
    -1.02
     supposedly
    -0.99
     since
    -0.97
    parently
    -0.93
    POSITIVE LOGITS
     nový
    1.23
    ￦
    1.21
     kontaktu
    1.15
     nová
    1.15
    ankan
    1.15
     combattre
    1.14
     gdzie
    1.13
     Einfluss
    1.13
     DEFENDANT
    1.13
     Wirkungen
    1.11
    Activations Density 0.000%

    No Known Activations