© 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. 45372
    Prev
    Next
    INDEX
    Explanations

    consist of / consisted of

    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
     række
    -0.69
    AGING
    -0.68
    જ
    -0.68
    supervised
    -0.67
     HasFactory
    -0.66
     Hubbard
    -0.66
     Rot
    -0.65
    terrible
    -0.65
    gathered
    -0.65
     grammi
    -0.65
    POSITIVE LOGITS
    στ
    0.79
    ordinal
    0.69
    äft
    0.67
     withdrawals
    0.66
     stucco
    0.66
    Cue
    0.65
    ttino
    0.65
     vierte
    0.64
    akers
    0.64
    厢
    0.64
    Activations Density 0.037%

    No Known Activations