© 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. 10-GEMMASCOPE-RES-131K
    7. 758
    Prev
    Next
    INDEX
    Explanations

    software migration

    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
    7
    -2.56
    8
    -2.53
            
    -2.53
    IANGLES
    -2.50
     это
    -2.50
    轳
    -2.47
    9
    -2.41
    '
    -2.34
    }$
    -2.30
    6
    -2.28
    POSITIVE LOGITS
    硖
    2.44
    唻
    2.33
     obstáculos
    2.16
    lahir
    2.16
    𝗪
    2.11
    ématique
    2.11
    鲮
    2.09
    ﺢ
    2.06
     souha
    2.05
     preocupar
    2.05
    Activations Density 0.012%

    No Known Activations