© 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. 130185
    Prev
    Next
    INDEX
    Explanations

    assets in file paths

    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_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
    籴
    -2.45
     ランプ
    -2.36
    ﺲ
    -2.19
    銫
    -2.13
    of
    -2.11
    鴆
    -2.11
    禤
    -2.09
     ſmall
    -2.08
     テープ
    -2.03
    缡
    -2.02
    POSITIVE LOGITS
    :
    2.44
     There
    2.31
     могут
    2.30
    Although
    2.27
    大多数
    2.17
     assets
    2.11
     somber
    2.02
    ...?
    1.99
    Typically
    1.98
    Most
    1.97
    Activations Density 0.006%

    No Known Activations