Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 289
    Prev
    Next
    INDEX
    Explanations

    many years or decades

    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_10/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
     it
    -1.71
    😂😂😂😂
    -1.60
    🤣🤣🤣
    -1.60
    }
    -1.57
    😂😂😂
    -1.57
    😂😂
    -1.53
    enfants
    -1.51
     talle
    -1.45
    🥲
    -1.45
     開封
    -1.44
    POSITIVE LOGITS
     years
    1.96
    瓩
    1.59
     ใน
    1.58
     schlechte
    1.53
    </em>
    1.52
     “
    1.52
    などで
    1.45
     многих
    1.45
     bessere
    1.45
     devido
    1.44
    Activations Density 0.022%

    No Known Activations