© 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. 22-GEMMASCOPE-RES-131K
    7. 34696
    Prev
    Next
    INDEX
    Explanations

    seeking something or solution

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

    The neuron detects first‐person expressions of confusion or uncertainty—i.e. admissions that “I” don’t understand, “must” be missing something, “messed up,” etc.

    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
    zości
    -1.02
     -->
    -1.02
     camara
    -1.01
     baterie
    -0.99
    onnaise
    -0.98
     filma
    -0.97
    ÑA
    -0.97
    ί
    -0.97
    ften
    -0.97
     puo
    -0.96
    POSITIVE LOGITS
     somehow
    2.33
     something
    2.19
     some
    2.02
     algún
    1.90
     somewhere
    1.83
     alguna
    1.66
     or
    1.63
     algum
    1.56
     maybe
    1.52
    何か
    1.46
    Activations Density 0.204%

    No Known Activations