Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11618
    Prev
    Next
    INDEX
    Explanations

    units of measurement and length

    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
     or
    -1.68
     this
    -1.59
     that
    -1.57
     of
    -1.51
     since
    -1.48
     for
    -1.38
     would
    -1.26
     which
    -1.25
     from
    -1.22
     will
    -1.21
    POSITIVE LOGITS
     coreana
    1.49
    Kamera
    1.33
     Irlanda
    1.30
     frustra
    1.28
     Palestina
    1.20
     fina
    1.20
     rempla
    1.19
     Siria
    1.18
    Karakter
    1.17
     gelatina
    1.17
    Activations Density 0.018%

    No Known Activations