© 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. 107526
    Prev
    Next
    INDEX
    Explanations

    required or necessary conditions

    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
    Liefer
    -1.16
    Выбор
    -1.04
     ejus
    -1.03
    뾰
    -1.02
    bungen
    -0.99
    內容簡介
    -0.98
    sätzlich
    -0.97
    Objetivos
    -0.96
    Почему
    -0.95
     发表于
    -0.95
    POSITIVE LOGITS
     needed
    8.69
     required
    7.53
     necessary
    7.25
    needed
    6.19
     Needed
    5.81
    required
    5.59
    Needed
    5.47
    necessary
    5.09
     Required
    5.06
    Required
    4.78
    Activations Density 0.579%

    No Known Activations