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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 53629
    Prev
    Next
    INDEX
    Explanations

    because of

    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_40_width_65k_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
    的不
    0.46
    ﺩ
    0.44
     relentless
    0.43
    国家的
    0.42
     unrelenting
    0.42
    
    0.41
    വരുടെ
    0.40
     onslaught
    0.40
    ]^{\
    0.39
     malades
    0.37
    POSITIVE LOGITS
     に
    0.44
     mappings
    0.43
     يش
    0.41
    จะ
    0.41
    包含了
    0.41
    श्ती
    0.40
    aket
    0.40
     envolve
    0.40
     beispielsweise
    0.40
     dotyczą
    0.40
    Activations Density 0.022%

    No Known Activations