© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118770
    Prev
    Next
    INDEX
    Explanations

    feature length

    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
     going
    -0.75
     ביותר
    -0.70
    賑
    -0.69
     بف
    -0.68
    sober
    -0.67
    териалы
    -0.65
    Colores
    -0.65
     yüzden
    -0.64
     sozial
    -0.64
    ụp
    -0.64
    POSITIVE LOGITS
     length
    4.03
     sized
    3.88
    length
    3.59
     size
    3.55
    sized
    3.31
    size
    3.22
    Length
    3.17
     Length
    3.03
    LENGTH
    2.73
     LENGTH
    2.73
    Activations Density 0.075%

    No Known Activations