© 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. 32386
    Prev
    Next
    INDEX
    Explanations

    departs from a lane

    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
    をご覧ください
    -1.12
     badly
    -0.99
    っていたので
    -0.98
     takže
    -0.89
     vastly
    -0.88
     continually
    -0.85
     Extensive
    -0.84
     its
    -0.84
     pinak
    -0.84
    ѱ
    -0.84
    POSITIVE LOGITS
     with
    1.86
     without
    1.34
     amidst
    1.15
     knowled
    1.05
     amid
    1.00
     despite
    0.90
     from
    0.84
    Լ
    0.84
     excit
    0.80
     Kullan
    0.79
    Activations Density 0.003%

    No Known Activations