© 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. 25805
    Prev
    Next
    INDEX
    Explanations

    how to do or make something

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

    The neuron activates on words that express permission or necessity (modal verbs like “can,” “must,” “allows,” “нужно,” 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_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
     entschieden
    -0.98
     attempting
    -0.89
    xD
    -0.88
    းက
    -0.86
     supplying
    -0.84
     brano
    -0.84
     attempt
    -0.84
     able
    -0.84
    attempt
    -0.80
     colegio
    -0.77
    POSITIVE LOGITS
    Solving
    0.94
     diversify
    0.94
     not
    0.94
     dimensionless
    0.88
    Stateless
    0.82
    solving
    0.81
     Solving
    0.80
    Postgres
    0.79
     manches
    0.79
     adherents
    0.79
    Activations Density 0.024%

    No Known Activations