© 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. 573
    Prev
    Next
    INDEX
    Explanations

    ending punctuation

    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
    me
    -1.05
     The
    -1.04
     L
    -1.03
    ues
    -1.02
    ja
    -1.00
    us
    -0.99
    ms
    -0.97
     Sha
    -0.96
    ica
    -0.96
     For
    -0.96
    POSITIVE LOGITS
    ↵↵↵
    1.85
    ↵↵↵↵
    1.66
    ↵↵↵↵↵
    1.57
    ↵↵↵↵↵↵
    1.40
    ↵↵↵↵↵↵↵
    1.34
    ↵↵
    1.30
    ↵↵↵↵↵↵↵↵
    1.27
    ↵↵↵↵↵↵↵↵↵↵
    1.20
    ↵↵↵↵↵↵↵↵↵
    1.19
     manguera
    1.09
    Activations Density 0.015%

    No Known Activations