© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12260
    Prev
    Next
    INDEX
    Explanations

    xhtml structure

    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
     to
    -1.70
     nového
    -1.35
    の変化
    -1.24
    verre
    -1.16
    などを
    -1.15
    を
    -1.15
    などが
    -1.11
     vermo
    -1.11
     praça
    -1.07
    renowned
    -1.06
    POSITIVE LOGITS
    While
    1.33
    Although
    1.25
    Penulis
    1.22
    愛知県
    1.22
    When
    1.21
    Hersteller
    1.19
    During
    1.15
    外部链接
    1.13
    福岡
    1.12
    Sometimes
    1.11
    Activations Density 0.017%

    No Known Activations