© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 1837
    Prev
    Next
    INDEX
    Explanations

    end-to-end communication

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

    The neuron strongly activates on numeric tokens (i.e. any standalone numbers or digit sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    zade
    -0.70
     ahşap
    -0.69
     Depois
    -0.69
    Yama
    -0.67
     obserw
    -0.66
    chalten
    -0.65
    unächst
    -0.65
     tanti
    -0.64
    بيوتر
    -0.64
    getActiveSheet
    -0.63
    POSITIVE LOGITS
     end
    6.56
    end
    3.86
    End
    3.83
     End
    3.81
     END
    2.97
    端
    2.86
    END
    2.81
    getEnd
    2.63
    エンド
    2.61
     конец
    2.34
    Activations Density 0.072%

    No Known Activations