© 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. 67123
    Prev
    Next
    INDEX
    Explanations

    forward to, trying, life

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

    The neuron spotlights positive‐tone descriptive words—especially warm, nice, family-oriented praise of a community or setting.

    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
     BOTH
    -1.32
     затем
    -1.27
     является
    -1.23
    bukkit
    -1.20
    курс
    -1.19
    AZIONE
    -1.18
     version
    -1.17
     kabát
    -1.17
     delito
    -1.16
     francia
    -1.15
    POSITIVE LOGITS
     they
    1.42
     [
    1.41
     dégustation
    1.30
    慢慢
    1.27
    Matéri
    1.26
    散策
    1.18
     основном
    1.17
    ensitive
    1.17
    )​
    1.17
    Vidéo
    1.15
    Activations Density 0.057%

    No Known Activations