© 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. 65541
    Prev
    Next
    INDEX
    Explanations

    brings something forth

    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
     Приступљено
    -1.17
    สำหรับ
    -1.16
     cordones
    -1.11
     anillos
    -1.09
     tornillos
    -1.09
     moteurs
    -1.08
    prech
    -1.08
     joyería
    -1.07
    Здесь
    -1.05
     compuesto
    -1.02
    POSITIVE LOGITS
     to
    2.77
     together
    2.38
     about
    2.16
     forth
    1.91
     along
    1.75
     into
    1.59
    Bring
    1.34
     Brings
    1.34
     added
    1.33
     alive
    1.31
    Activations Density 0.021%

    No Known Activations