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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 23905
    Prev
    Next
    INDEX
    Explanations

    objects, tasks, or issues

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

    The neuron consistently lights up on common content nouns (e.g. banner, heart, error, cars, lights).

    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
    Cevap
    -0.99
     deose
    -0.99
    的气息
    -0.98
     vitales
    -0.96
    گار
    -0.96
     certamente
    -0.93
     hierzu
    -0.93
    将她
    -0.93
     einerseits
    -0.92
    亍
    -0.92
    POSITIVE LOGITS
     that
    2.56
     which
    1.42
     they
    1.37
     itself
    1.33
     but
    1.32
     thing
    1.27
     которое
    1.23
    FORCEMENT
    1.20
     of
    1.19
    ที่
    1.17
    Activations Density 0.188%

    No Known Activations