© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103385
    Prev
    Next
    INDEX
    Explanations

    regularly or usually

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

    The neuron flags enumerated technical action verbs (e.g. “processes,” “compiles,” “stores,” “communicates,” etc.) in formal/system descriptions.

    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
     especially
    -0.89
     labai
    -0.86
     kila
    -0.81
     zile
    -0.81
    ņem
    -0.80
     very
    -0.79
    味の
    -0.79
    GUAR
    -0.79
    至今
    -0.78
     around
    -0.77
    POSITIVE LOGITS
     or
    1.14
     predominantly
    1.05
     almeno
    1.02
     delincuentes
    1.00
     habitually
    0.99
     Regularly
    0.98
     regularly
    0.97
    ITHER
    0.97
    直接
    0.96
    通常
    0.96
    Activations Density 0.085%

    No Known Activations