© 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. 75676
    Prev
    Next
    INDEX
    Explanations

    during specific events or time periods

    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
    ;
    -2.11
    >
    -2.06
    A
    -2.02
     sicheren
    -1.86
    “
    -1.84
    最初は
    -1.76
     leichten
    -1.74
    th
    -1.70
    lo
    -1.67
     is
    -1.67
    POSITIVE LOGITS
    蓠
    2.53
    ⑊
    2.50
    瞜
    2.50
    ꪻ
    2.30
    providedIn
    2.22
    纮
    2.19
    嘁
    2.11
    ࿚
    2.09
    ᯅ
    2.06
    METHODOLOGY
    2.03
    Activations Density 0.012%

    No Known Activations