© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110889
    Prev
    Next
    INDEX
    Explanations

    certainty

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

    The neuron detects words expressing certainty or confidence (e.g., “certain,” “sure”).

    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
    dö
    -1.26
     löst
    -1.17
    視野
    -1.11
    掟
    -1.08
     schlägt
    -1.08
    zembro
    -1.05
    </sup>
    -1.03
    Jawab
    -1.02
    Sebelum
    -1.02
     fährt
    -1.02
    POSITIVE LOGITS
     of
    3.61
     that
    2.56
     they
    1.24
     about
    1.17
     SURE
    1.15
     ši
    1.12
     medži
    1.07
    ੧
    1.07
    ly
    1.02
    ของ
    1.02
    Activations Density 0.020%

    No Known Activations