© 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. 34-GEMMASCOPE-RES-131K
    7. 64885
    Prev
    Next
    INDEX
    Explanations

    named entities and locations

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

    The neuron fires on terminology and context describing asteroids (e.g. asteroid names, the asteroid belt, orbits, and related planetary references).

    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
    sanity
    -0.84
     ALLEN
    -0.81
     Blvd
    -0.76
    zesi
    -0.73
     menuItem
    -0.71
    ']")
    -0.69
    にします
    -0.69
     através
    -0.69
     diritto
    -0.69
    [])
    -0.68
    POSITIVE LOGITS
    WOOD
    0.84
    లాలు
    0.81
    CLES
    0.79
    SMC
    0.77
    örk
    0.76
     WRITE
    0.76
     сопер
    0.76
     Mayfield
    0.75
     hatched
    0.75
    HOLD
    0.75
    Activations Density 0.006%

    No Known Activations