© 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. 10-GEMMASCOPE-RES-131K
    7. 130131
    Prev
    Next
    INDEX
    Explanations

    doubt and consideration

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

    This neuron detects speculative or hedging language—words and phrases that signal uncertainty, possibility, or considered questioning (e.g. might, questioned whether, considered, expect).

    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
     These
    -1.70
     these
    -1.32
     the
    -1.22
     The
    -1.20
     Это
    -1.16
     gelingt
    -1.07
    éma
    -1.06
    おそらく
    -1.06
     seine
    -1.06
     he
    -1.06
    POSITIVE LOGITS
    quantidade
    1.24
     tradução
    1.23
    geable
    1.21
     çocuklar
    1.20
    liegenden
    1.20
                            
    1.20
    нару
    1.18
    没
    1.17
     at
    1.17
     edile
    1.16
    Activations Density 0.079%

    No Known Activations