© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 588
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    </b>
    -1.59
    two
    -1.58
    NO
    -1.57
    excellents
    -1.50
    nyard
    -1.46
    different
    -1.45
    RE
    -1.41
    BE
    -1.40
    best
    -1.40
     to
    -1.39
    POSITIVE LOGITS
    国庆
    1.49
    パッケージ
    1.48
    本章
    1.48
    第八
    1.45
     interruptor
    1.45
    ：……
    1.41
    lihatan
    1.39
    近年来
    1.39
    Quiénes
    1.38
    オーストラリア
    1.37
    Activations Density 0.207%

    No Known Activations