© 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. 118690
    Prev
    Next
    INDEX
    Explanations

    words starting with Mon

    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
     however
    -0.91
    <bos>
    -0.85
    そして
    -0.82
    芯
    -0.77
     lạc
    -0.76
    だが
    -0.76
    ettare
    -0.75
    Однако
    -0.75
     hingga
    -0.73
    TIR
    -0.73
    POSITIVE LOGITS
     Mon
    1.39
     mon
    1.27
    mon
    1.23
     MON
    1.20
    Mon
    1.20
     مون
    1.04
    MON
    0.98
     Monde
    0.98
    えっ
    0.97
     моно
    0.92
    Activations Density 0.023%

    No Known Activations