© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73570
    Prev
    Next
    INDEX
    Explanations

    read more, see more, continue reading

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags link-style “more” prompts (e.g. “More information,” “Read more”) that signal a continuation or call to action.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     (
    -1.82
     all
    -1.46
     or
    -1.25
    ggars
    -1.24
    いただけます
    -1.20
     their
    -1.16
     every
    -1.15
    ☎️
    -1.15
     using
    -1.14
     from
    -1.13
    POSITIVE LOGITS
     alcune
    1.45
     wielu
    1.38
     molte
    1.34
    ਗ਼
    1.32
     durante
    1.32
     DURING
    1.29
     AMAZING
    1.28
     molti
    1.28
     magnific
    1.27
    苼
    1.27
    Activations Density 0.014%

    No Known Activations