© 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. 49264
    Prev
    Next
    INDEX
    Explanations

    certainty or lack thereof

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

    The neuron detects words in common idiomatic expressions that emphasize removing or dispelling doubt (e.g. “remove all doubt,” “without a doubt,” “beyond doubt”).

    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
     inap
    -0.81
     peta
    -0.80
     stocker
    -0.80
     Medit
    -0.79
    的游戏
    -0.79
     Tribun
    -0.79
     समस्या
    -0.79
    kami
    -0.78
     Gators
    -0.78
     grotes
    -0.77
    POSITIVE LOGITS
     doubt
    2.16
     сом
    1.40
     shadow
    1.36
     uncertainty
    1.30
     question
    1.21
    doubt
    1.13
    shadow
    1.13
     doubts
    1.12
     Shadow
    1.09
    Shadow
    1.02
    Activations Density 0.019%

    No Known Activations