© 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. 285
    Prev
    Next
    INDEX
    Explanations

    RK, SSC, xor, convertView

    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
     It
    -3.05
    五三
    -2.36
     Traditionally
    -2.25
     From
    -2.23
     Surprisingly
    -2.22
    ahuila
    -2.22
     were
    -2.17
    ization
    -2.17
    What
    -2.16
    Ꮚ
    -2.14
    POSITIVE LOGITS
     builds
    2.75
    ↵↵
    2.47
     selben
    2.41
     ホビー
    2.36
     importantly
    2.23
    .”
    2.16
     について
    2.14
     us
    2.13
    轤
    2.09
    和我
    2.08
    Activations Density 0.004%

    No Known Activations