© 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. 10-GEMMASCOPE-RES-131K
    7. 90385
    Prev
    Next
    INDEX
    Explanations

    выбор между вариантами

    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
     '
    -2.48
    ’
    -2.41
     =
    -2.41
    rd
    -2.34
    an
    -2.34
    >
    -2.28
     inadequ
    -2.25
    ):
    -2.25
    $,
    -2.19
    9
    -2.17
    POSITIVE LOGITS
    镔
    3.52
    ྵ
    3.33
    媜
    2.66
    钲
    2.64
    🕗
    2.59
     blevet
    2.55
    輋
    2.45
    鎹
    2.44
    噲
    2.42
    稣
    2.38
    Activations Density 0.001%

    No Known Activations