© 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. 70800
    Prev
    Next
    INDEX
    Explanations

    reshape, concat, combining

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

    The neuron activates on numeric tokens (integers or decimals).

    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
    zheim
    -1.30
    }
    -1.29
    ი
    -1.27
    crania
    -1.20
    ogues
    -1.19
    ogical
    -1.16
    ec
    -1.13
     avoid
    -1.11
     控
    -1.11
     岁
    -1.08
    POSITIVE LOGITS
    cucumber
    1.21
    ޏ
    1.13
    クッション
    1.13
     kiti
    1.13
    瞠
    1.09
    forgot
    1.09
    [*
    1.09
    ཥ
    1.08
     nécess
    1.07
    久しぶりの
    1.07
    Activations Density 0.001%

    No Known Activations