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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38749
    Prev
    Next
    INDEX
    Explanations

    its [noun]

    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
     kombinasi
    -1.72
    ᨈ
    -1.54
     edisi
    -1.51
     اگر
    -1.42
     kemungkinan
    -1.38
     if
    -1.34
     ketika
    -1.34
     identitas
    -1.34
     brinde
    -1.31
    了些
    -1.31
    POSITIVE LOGITS
    Understand
    1.27
     program
    1.26
     product
    1.23
     website
    1.19
     žaid
    1.14
    <em>
    1.13
     system
    1.13
    Anybody
    1.12
     įsi
    1.11
     hong
    1.10
    Activations Density 0.046%

    No Known Activations