© 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. 1379
    Prev
    Next
    INDEX
    Explanations

    end of development

    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
     första
    -1.21
    first
    -1.19
     første
    -1.13
     первым
    -1.11
    Initial
    -1.11
     πρώ
    -1.06
     первого
    -1.06
    initial
    -1.04
     eerste
    -1.02
     הראשון
    -1.02
    POSITIVE LOGITS
     late
    5.28
    Late
    3.70
    late
    3.70
     Late
    3.52
     later
    3.39
     LATE
    3.16
    LATE
    2.94
     cuối
    2.72
     towards
    2.61
    後半
    2.53
    Activations Density 0.099%

    No Known Activations