© 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. 73979
    Prev
    Next
    INDEX
    Explanations

    ability, capability, or suitability

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

    The neuron fires on the normative/specification language of technical requirements (e.g. “must,” “should,” “be,” adjectives like “simple,” “efficient,” “proof,” etc.).

    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
     only
    -1.20
    Langkah
    -1.12
    ^{}
    -1.09
     now
    -1.07
     using
    -1.02
     almost
    -1.02
     more
    -1.01
     cuma
    -1.00
    áct
    -0.99
    Berdasarkan
    -0.98
    POSITIVE LOGITS
     بتوان
    1.45
    preferably
    1.38
     able
    1.32
    能够
    1.31
     ability
    1.29
     zodat
    1.27
     Preferably
    1.24
     preferably
    1.19
     affordable
    1.18
     möglichst
    1.18
    Activations Density 0.244%

    No Known Activations