© 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. 33697
    Prev
    Next
    INDEX
    Explanations

    official scoring and analysis

    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
     height
    -1.94
     altura
    -1.71
    height
    -1.69
     hauteur
    -1.65
    HEIGHT
    -1.48
    Height
    -1.46
     heights
    -1.45
     Height
    -1.44
     Höhe
    -1.40
    getHeight
    -1.23
    POSITIVE LOGITS
     score
    1.35
     Congressional
    1.29
     analysis
    1.23
     scoring
    1.22
     independent
    1.21
     scored
    1.18
     analyses
    1.16
     Score
    1.13
     estimate
    1.11
     scores
    1.11
    Activations Density 0.016%

    No Known Activations