© 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. 129636
    Prev
    Next
    INDEX
    Explanations

    pastes this link to email

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

    The neuron activates on verbs that denote actions or operations (e.g. “redirects,” “detecting,” “embed,” “link,” “wake”).

    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
     our
    -2.00
     many
    -1.67
     work
    -1.34
     जबकि
    -1.26
     thousands
    -1.23
     लेकिन
    -1.23
    vají
    -1.21
     your
    -1.21
     lament
    -1.20
     do
    -1.19
    POSITIVE LOGITS
     triomphe
    1.30
     могу
    1.21
     récents
    1.19
     podido
    1.13
    力气
    1.13
     ANTON
    1.12
     Proyecto
    1.11
    Ꮔ
    1.11
     drapeau
    1.10
     admirer
    1.08
    Activations Density 0.222%

    No Known Activations