© 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. 109187
    Prev
    Next
    INDEX
    Explanations

    statements of fact or report

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

    The neuron activates on words expressing subjective stance or evaluation—i.e. opinion, belief, advice, or judgment terms.

    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
    在我们
    -1.05
    在你
    -1.05
    ̑
    -0.92
    让我们
    -0.91
    在她
    -0.91
     Experten
    -0.90
    在中国
    -0.90
    тъ
    -0.89
     uppgifter
    -0.86
     zvuk
    -0.86
    POSITIVE LOGITS
     there
    3.88
     they
    3.69
     it
    3.55
     this
    2.36
     we
    2.23
     these
    2.11
     you
    2.09
     nobody
    1.92
     someone
    1.90
     everything
    1.83
    Activations Density 0.138%

    No Known Activations