© 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. 39153
    Prev
    Next
    INDEX
    Explanations

    questions and code snippets

    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
     for
    -1.74
    Since
    -1.61
     Since
    -1.59
    All
    -1.59
    Because
    -1.55
     all
    -1.55
     reduce
    -1.53
     Despite
    -1.53
    When
    -1.52
     at
    -1.51
    POSITIVE LOGITS
    為に
    1.77
     dezelve
    1.55
    honestly
    1.52
    殽
    1.52
    chose
    1.49
     zoude
    1.48
    ཿ
    1.47
    hmmm
    1.45
    
    1.45
     dinosaurios
    1.45
    Activations Density 0.001%

    No Known Activations