© 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. 10-GEMMASCOPE-RES-131K
    7. 73738
    Prev
    Next
    INDEX
    Explanations

    Harper and HRC entities

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

    The neuron primarily detects the proper name “Harper.”

    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
    \
    -3.09
     With
    -2.61
    ")
    -2.58
     '
    -2.48
    </em>
    -2.48
    ers
    -2.36
     enviada
    -2.33
     technisch
    -2.33
     Therefore
    -2.28
     estratégica
    -2.28
    POSITIVE LOGITS
    鲼
    2.69
    ℣
    2.55
    徬
    2.50
    StoryboardSegue
    2.50
    涐
    2.39
    er
    2.27
    providedIn
    2.20
     teraz
    2.20
    猡
    2.16
     him
    2.11
    Activations Density 0.001%

    No Known Activations