© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34029
    Prev
    Next
    INDEX
    Explanations

    II)- , Iterators, Submicron, Jake Jones, In utero

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

    Roman numerals, particularly "II" in academic or scientific contexts.

    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
     in
    -1.64
     Française
    -1.18
    Ưu
    -1.15
    ってしまった
    -1.14
     its
    -1.13
    inize
    -1.13
     évé
    -1.12
     any
    -1.08
    formaz
    -1.07
     безопасность
    -1.07
    POSITIVE LOGITS
     procéder
    1.22
    Aquí
    1.22
    Ambos
    1.15
     赤ちゃん
    1.14
     entrambi
    1.14
     exportación
    1.09
    Recept
    1.08
    Sabato
    1.06
    Tú
    1.05
    Descriere
    1.05
    Activations Density 0.000%

    No Known Activations