© 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. 48320
    Prev
    Next
    INDEX
    Explanations

    invitations to attend or participate

    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
    ↵
    -1.30
    </b>
    -1.27
     tandis
    -1.19
    きち
    -1.18
     avven
    -1.18
     necesita
    -1.15
     It
    -1.14
    coupled
    -1.14
     Krzysz
    -1.13
     I
    -1.12
    POSITIVE LOGITS
    Даже
    1.34
    Bahkan
    1.33
    Ayrıca
    1.32
    我们在
    1.31
    perity
    1.30
    Meskipun
    1.29
    Ϯ
    1.27
    avyzd
    1.26
    amment
    1.23
    Mereka
    1.23
    Activations Density 0.018%

    No Known Activations