© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118631
    Prev
    Next
    INDEX
    Explanations

    words ending in 'it' or 'ith'

    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
    human
    -1.02
    ish
    -1.00
    hint
    -0.97
    husband
    -0.91
    hardware
    -0.91
    hus
    -0.90
    hand
    -0.89
    her
    -0.88
    ed
    -0.87
    hw
    -0.87
    POSITIVE LOGITS
    ting
    1.40
    ters
    1.30
    ted
    1.07
    tering
    1.06
    tings
    0.98
    tingly
    0.86
     intéress
    0.85
    годно
    0.84
    tttt
    0.82
     インテリア
    0.81
    Activations Density 0.162%

    No Known Activations