© 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. 75419
    Prev
    Next
    INDEX
    Explanations

    free trial offer

    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
     landslide
    -0.71
    飯店
    -0.68
    update
    -0.68
    お値段
    -0.67
     změ
    -0.66
    onais
    -0.66
    お酒
    -0.65
    ビタミン
    -0.65
     serangan
    -0.64
    bashrc
    -0.63
    POSITIVE LOGITS
     trial
    5.59
    trial
    4.31
     Trial
    4.22
    Trial
    4.03
     trials
    4.03
     TRIAL
    3.48
     Trials
    3.30
    trials
    3.08
    试
    3.03
    Trials
    2.98
    Activations Density 0.065%

    No Known Activations