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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12179
    Prev
    Next
    INDEX
    Explanations

    unicode strings and quotes

    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
     any
    -1.66
     other
    -1.40
     our
    -1.39
     various
    -1.34
     some
    -1.31
     enhancing
    -1.28
     additional
    -1.28
     those
    -1.23
     all
    -1.22
     just
    -1.17
    POSITIVE LOGITS
     '"
    1.40
     '
    1.30
     DURING
    1.28
     "'
    1.21
    CDATA
    1.20
     especialmente
    1.20
     exceedingly
    1.15
     folgender
    1.13
     !!!!
    1.12
     ARISING
    1.12
    Activations Density 0.007%

    No Known Activations