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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 29380
    Prev
    Next
    INDEX
    Explanations

    code delimiters and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    含む
    0.44
     тощо
    0.44
     ます
    0.43
     другие
    0.42
    issances
    0.42
    }`,
    0.42
    }|$
    0.41
    
    0.40
    Ͻ
    0.40
    )]$
    0.39
    POSITIVE LOGITS
     Greetings
    0.43
     Summer
    0.42
     Assessment
    0.42
     Trial
    0.42
     Eaton
    0.41
     Services
    0.41
     of
    0.40
     Weekend
    0.40
     Smart
    0.40
     Valor
    0.40
    Activations Density 0.001%

    No Known Activations