© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36002
    Prev
    Next
    INDEX
    Explanations

    language codes and names

    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
     only
    -1.46
     some
    -1.38
     many
    -1.30
     several
    -1.22
     three
    -1.19
    ﾋ
    -1.19
     both
    -1.16
     every
    -1.14
     numerous
    -1.14
     because
    -1.12
    POSITIVE LOGITS
     delightfully
    1.15
     insanely
    1.13
     revamped
    1.10
     quintessential
    1.08
    uch
    1.08
     nimmer
    1.06
     في
    1.02
    Ĩ
    1.02
     '',
    1.02
    referred
    1.01
    Activations Density 0.009%

    No Known Activations