© 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. 31189
    Prev
    Next
    INDEX
    Explanations

    words starting with blast

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

    The neuron fires on occurrences of the morpheme “blast” (e.g. in words like blastomogenic, blastula, blastocyst, blastogenesis).

    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
    żym
    -0.88
     brasil
    -0.88
     Organics
    -0.87
     Patents
    -0.85
     Upan
    -0.84
    ▴
    -0.83
     Constructors
    -0.82
    蓐
    -0.82
    ele
    -0.81
     auctor
    -0.81
    POSITIVE LOGITS
     blast
    1.34
    oise
    1.31
     Blast
    1.31
    ocy
    1.19
     furnace
    1.18
     吹
    1.00
    Blast
    1.00
     Blas
    0.99
    blast
    0.98
     blas
    0.91
    Activations Density 0.011%

    No Known Activations