© 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. 22-GEMMASCOPE-RES-131K
    7. 159
    Prev
    Next
    INDEX
    Explanations

    excited states and transitions

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

    terms related to quantum states and energy levels in scientific literature.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     APPELLANT
    -1.38
     السياس
    -1.28
     الحكومة
    -1.23
    gnes
    -1.13
     passato
    -1.07
     décider
    -1.05
    就想
    -1.04
    торт
    -1.03
     obtenir
    -1.03
     créer
    -1.03
    POSITIVE LOGITS
     in
    1.24
     certamen
    1.11
     at
    1.10
     that
    1.10
     heightened
    1.09
    CHREIBUNG
    1.09
     céramique
    1.08
     overtly
    1.08
     having
    1.07
     meticulously
    1.07
    Activations Density 0.051%

    No Known Activations