© 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. 116244
    Prev
    Next
    INDEX
    Explanations

    phrases describing cause, basis, or action

    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
     diversos
    -1.39
    很多的
    -1.38
     terse
    -1.28
    &
    -1.27
    皷
    -1.27
     contempl
    -1.26
    H
    -1.26
    ︲
    -1.23
    盉
    -1.23
    ための
    -1.23
    POSITIVE LOGITS
    Every
    1.43
    Our
    1.41
    apropri
    1.37
     with
    1.32
     utterly
    1.30
     sehr
    1.30
     and
    1.27
     initiatives
    1.27
     by
    1.24
    larım
    1.24
    Activations Density 0.132%

    No Known Activations