© 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. 61435
    Prev
    Next
    INDEX
    Explanations

    words ending in ink

    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
    咈
    -2.91
     “
    -2.89
     you
    -2.58
     Other
    -2.44
     relieve
    -2.41
    ка
    -2.41
    <td>
    -2.36
    arwal
    -2.31
    .”
    -2.27
     Placing
    -2.27
    POSITIVE LOGITS
    了很多
    2.42
    Ꮈ
    2.39
    跸
    2.38
    튿
    2.38
     orientale
    2.36
     australiano
    2.33
    裡的
    2.28
    潆
    2.27
     bénéficiaire
    2.27
    ſten
    2.27
    Activations Density 0.014%

    No Known Activations