© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59994
    Prev
    Next
    INDEX
    Explanations

    super constructor calls

    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_34/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
    base
    -1.63
     base
    -1.51
    Base
    -1.31
     Base
    -1.24
    ベース
    -1.23
     BASE
    -1.16
    BASE
    -1.08
     bases
    -1.02
     this
    -0.93
     nyeri
    -0.92
    POSITIVE LOGITS
    ఁ
    0.81
    cyclopedia
    0.80
     Verhältnis
    0.77
     beobach
    0.76
     sorgfäl
    0.76
    whence
    0.73
     Obtaining
    0.72
     Bedarf
    0.71
     güns
    0.71
     flexibilidad
    0.71
    Activations Density 0.014%

    No Known Activations