© 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. 118981
    Prev
    Next
    INDEX
    Explanations

    words starting with Ad

    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
     pochi
    -0.99
     although
    -0.93
     few
    -0.93
    どちらも
    -0.90
    ້
    -0.84
    จึง
    -0.82
    embolso
    -0.81
    って感じ
    -0.80
    сього
    -0.80
    izations
    -0.79
    POSITIVE LOGITS
    Ад
    1.12
     Ad
    1.12
    Ad
    0.98
     AD
    0.96
    鶏
    0.93
     Ад
    0.90
     adh
    0.88
     souvent
    0.85
     esetben
    0.84
     hoc
    0.84
    Activations Density 0.126%

    No Known Activations