© 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. 70958
    Prev
    Next
    INDEX
    Explanations

    booking, session, account

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

    The neuron activates on numeric literals (tokens consisting of digits).

    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
    <bos>
    -1.99
    Following
    -1.51
    因为
    -1.34
    Untuk
    -1.30
    Since
    -1.28
    สำหรับ
    -1.28
    Like
    -1.27
     only
    -1.27
    Having
    -1.26
    With
    -1.24
    POSITIVE LOGITS
     “
    1.23
    ものが
    1.18
     salvajes
    1.13
    en
    1.08
    方に
    1.06
     poseen
    1.06
    者が
    1.04
    ものである
    1.04
     např
    1.01
    –
    1.00
    Activations Density 0.004%

    No Known Activations