© 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. 22-GEMMASCOPE-RES-131K
    7. 67879
    Prev
    Next
    INDEX
    Explanations

    expressing beliefs and contributing ideas

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

    This neuron responds to content-bearing words—especially nouns and verbs—in formal encyclopedic or academic descriptions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     when
    -1.82
     there
    -1.53
     will
    -1.44
    when
    -1.38
     if
    -1.32
    ּוֹ
    -1.28
     before
    -1.26
    するの
    -1.26
     then
    -1.25
    しなければ
    -1.25
    POSITIVE LOGITS
     EVERYTHING
    1.65
     sacerdotes
    1.39
     LOTS
    1.32
     peinado
    1.30
     controversi
    1.28
    罫
    1.26
     ám
    1.23
     comptes
    1.23
    itern
    1.23
     discí
    1.21
    Activations Density 0.032%

    No Known Activations