© 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. 34-GEMMASCOPE-RES-131K
    7. 1716
    Prev
    Next
    INDEX
    Explanations

    search form

    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_34/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
    !',
    -1.14
    !»
    -1.08
    !}
    -1.03
    颌
    -1.02
    !'
    -1.02
    !');
    -0.98
    頜
    -0.97
    !')
    -0.97
    !</
    -0.96
    !",
    -0.95
    POSITIVE LOGITS
     It
    1.59
     There
    1.47
     I
    1.45
     If
    1.32
     This
    1.30
     Let
    1.28
     You
    1.24
     We
    1.22
     Do
    1.14
     Are
    1.12
    Activations Density 0.003%

    No Known Activations