© 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. 11560
    Prev
    Next
    INDEX
    Explanations

    hour or hours

    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
    ﱠ
    -2.59
    CHREIB
    -2.56
     každý
    -2.30
    loween
    -2.28
    Ἢ
    -2.28
     primeiros
    -2.27
     caminhos
    -2.22
     fatos
    -2.20
     pomaga
    -2.19
    になりました
    -2.17
    POSITIVE LOGITS
    .
    3.41
    le
    3.08
     работы
    2.41
    ):
    2.17
     alignItems
    2.14
    for
    2.14
     justifyContent
    2.14
    洐
    2.13
    href
    2.13
    all
    2.13
    Activations Density 0.021%

    No Known Activations