© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25894
    Prev
    Next
    INDEX
    Explanations

    states and actions

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

    The neuron activates on words conveying subjective evaluation or hedging (e.g. “pretty,” “possible,” “seems,” “wondering,” “perfect”).

    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
    Nazionale
    -1.21
    mahaman
    -1.05
     Евгений
    -1.05
     it
    -1.03
     sowohl
    -1.02
     ilustracji
    -1.02
     during
    -1.00
     饰
    -0.98
     several
    -0.97
    してしまった
    -0.97
    POSITIVE LOGITS
    Quanto
    1.13
     vogel
    1.05
     szint
    1.02
    Odpovědět
    1.01
     ebenfalls
    0.98
    ,;
    0.98
     juf
    0.96
    Mvh
    0.96
     acclaimed
    0.95
     cib
    0.95
    Activations Density 0.022%

    No Known Activations