© 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. 22-GEMMASCOPE-RES-131K
    4. 67931
    Prev
    Next
    INDEX
    Explanations

    go followed by direction

    np_acts-logits-general · gemini-2.5-flash-lite

    the verb “go” in its various contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    r
    -2.45
    when
    -2.39
    you
    -2.36
    吆
    -2.30
    m
    -2.30
    
    -2.28
    これが
    -2.22
    それが
    -2.20
    躄
    -2.19
     ingenting
    -2.17
    POSITIVE LOGITS
     to
    3.81
     Our
    2.81
     into
    2.73
     我们
    2.33
    ⬈
    2.03
    ichteten
    2.02
     mehrere
    2.00
     out
    2.00
     through
    1.98
    ."
    1.96
    Activations Density 0.058%

    No Known Activations