© 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. 34713
    Prev
    Next
    INDEX
    Explanations

    names and topics

    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
     ungefär
    -1.27
     people
    -1.24
     mainly
    -1.13
     primarily
    -1.13
     always
    -1.08
     on
    -1.04
     phénom
    -1.04
     notable
    -1.02
     PUSTAKA
    -1.01
    ESTY
    -1.00
    POSITIVE LOGITS
    vantaged
    1.21
     obicei
    1.20
     テープ
    1.18
    rement
    1.16
     clicar
    1.14
    rosion
    1.13
    etton
    1.13
     exhilarating
    1.11
    }\}
    1.11
    rigation
    1.09
    Activations Density 0.003%

    No Known Activations