© 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. 105726
    Prev
    Next
    INDEX
    Explanations

    regulating and adjusted

    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
     extrêmement
    -1.58
    ⽼
    -1.56
    ケモン
    -1.55
     naciones
    -1.55
     ſeveral
    -1.51
    蹰
    -1.48
     Perſ
    -1.48
    ibel
    -1.46
    蕖
    -1.45
     România
    -1.44
    POSITIVE LOGITS
    A
    1.81
     the
    1.65
     with
    1.63
     your
    1.58
    With
    1.35
    one
    1.34
    E
    1.30
     one
    1.28
    up
    1.27
     out
    1.26
    Activations Density 0.060%

    No Known Activations