© 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. 79699
    Prev
    Next
    INDEX
    Explanations

    not/no/didn't + verb

    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
     calendriers
    -1.31
    ：……
    -1.29
    mäß
    -1.26
     gorro
    -1.24
     incrí
    -1.21
     tampaknya
    -1.20
     selalu
    -1.19
     dilaporkan
    -1.19
     kadang
    -1.18
     périodes
    -1.18
    POSITIVE LOGITS
     even
    1.47
     any
    1.45
     immediately
    1.35
     further
    1.20
     at
    1.20
     either
    1.16
     anything
    1.16
    Any
    1.14
     more
    1.13
     ask
    1.11
    Activations Density 0.015%

    No Known Activations