© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12894
    Prev
    Next
    INDEX
    Explanations

    evidence that

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

    The neuron fires on occurrences of “evidence,” especially in phrases like “there is evidence that.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     there
    -1.80
    There
    -1.73
     foundational
    -1.54
     inspiring
    -1.52
     successivamente
    -1.48
    コロナ禍
    -1.45
     disimpan
    -1.41
     surprisingly
    -1.38
    インスタ
    -1.37
     aqueles
    -1.36
    POSITIVE LOGITS
     is
    2.19
     you
    1.70
     hagan
    1.60
    rógeno
    1.58
     considérons
    1.55
    利
    1.55
     marav
    1.54
     আম
    1.53
     avec
    1.52
    疴
    1.50
    Activations Density 0.040%

    No Known Activations