© 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. 129868
    Prev
    Next
    INDEX
    Explanations

    nouns followed by actions or states

    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
    ÖR
    -1.48
    ܖ
    -1.35
     with
    -1.32
    ebly
    -1.28
     masalah
    -1.23
     bluz
    -1.22
    ⃢
    -1.21
    believe
    -1.16
     án
    -1.16
     akrab
    -1.16
    POSITIVE LOGITS
     is
    1.52
     are
    1.38
     OGSÅ
    1.34
     послед
    1.20
     zależ
    1.18
     was
    1.18
     will
    1.17
     costs
    1.13
     aparatos
    1.12
     fyra
    1.11
    Activations Density 0.090%

    No Known Activations