© 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. 47745
    Prev
    Next
    INDEX
    Explanations

    reading and narration

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

    The neuron strongly activates on occurrences of the auxiliary “be” (especially in passive‐voice or infinitival “to be” constructions).

    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
     ajuta
    -0.82
    طلق
    -0.75
     Gespräche
    -0.69
    präche
    -0.68
    umpf
    -0.67
    sikan
    -0.67
    を書く
    -0.65
    usehen
    -0.65
    }_{
    -0.64
    ições
    -0.63
    POSITIVE LOGITS
     read
    5.53
     reading
    4.88
    read
    4.06
     reads
    3.98
     readings
    3.81
    reading
    3.64
     Reading
    3.50
    Reading
    3.48
    读
    3.27
     Read
    3.20
    Activations Density 0.049%

    No Known Activations