© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79544
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and digits

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     situe
    -1.16
    があります
    -1.10
    ですが
    -1.09
    日を
    -1.08
     salga
    -1.06
     aucun
    -1.03
     llegue
    -1.02
    車は
    -1.00
     aujourd
    -0.98
    ține
    -0.98
    POSITIVE LOGITS
    為に
    1.22
    感じで
    1.00
     makes
    0.98
    끄
    0.98
     (!__
    0.96
    သ
    0.95
     früher
    0.92
     vermutlich
    0.91
    engager
    0.91
    ようで
    0.90
    Activations Density 0.015%

    No Known Activations