© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2739
    Prev
    Next
    INDEX
    Explanations

    technical questions

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

    This neuron responds to biological classification and descriptive taxonomy terms (e.g. flora, species, composition, structure, type, evergreen, tropical, rainforest).

    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
     by
    -1.08
    magitan
    -1.05
     this
    -1.01
     a
    -0.98
     kỷ
    -0.95
    Ŏ
    -0.93
     voordat
    -0.93
     dijeron
    -0.91
     without
    -0.90
     blauwe
    -0.90
    POSITIVE LOGITS
     normes
    1.04
     interrom
    1.04
     Palestina
    1.02
    𝔢
    0.97
     campesinos
    0.96
    峮
    0.96
     constructeur
    0.95
     campes
    0.94
    Preço
    0.94
    nc
    0.94
    Activations Density 0.001%

    No Known Activations