© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47871
    Prev
    Next
    INDEX
    Explanations

    past tense statements by "I"

    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
    非常好
    -0.99
    zzet
    -0.98
    フレット
    -0.97
     iNdEx
    -0.94
    SYNOPSIS
    -0.88
    stab
    -0.83
    ủng
    -0.83
     StringTokenizer
    -0.82
    DataInputStream
    -0.80
    prech
    -0.80
    POSITIVE LOGITS
     will
    1.68
     miss
    1.17
     knew
    1.01
     feel
    0.95
     misses
    0.94
    Transcripción
    0.91
    Transkript
    0.91
    Transcriptie
    0.90
     only
    0.88
     loved
    0.87
    Activations Density 0.010%

    No Known Activations