© 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. 66652
    Prev
    Next
    INDEX
    Explanations

    PHP language keys: column, order

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

    The neuron flags lines in block comments that begin with an asterisk (e.g., copyright/disclaimer lines).

    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
     this
    -1.48
     more
    -1.38
     one
    -1.32
     before
    -1.30
     from
    -1.27
     not
    -1.26
     there
    -1.24
     all
    -1.22
     at
    -1.20
     on
    -1.15
    POSITIVE LOGITS
     Dinas
    1.22
     faciliter
    1.21
     luscious
    1.12
     lading
    1.12
     accu
    1.11
     RST
    1.08
     Эти
    1.06
     overla
    1.05
    ยม
    1.05
     ´
    1.03
    Activations Density 0.000%

    No Known Activations