© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119733
    Prev
    Next
    INDEX
    Explanations

    prerequisites and preparedness

    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
    with
    -2.88
     với
    -2.63
    -
    -2.58
    s
    -2.28
    }$.
    -2.20
    )
    -2.19
    渽
    -2.11
     выборе
    -2.09
    銪
    -2.08
    猻
    -2.05
    POSITIVE LOGITS
     verdaderamente
    2.73
     
    2.55
    ㌧
    2.53
     kimdir
    2.48
    
    2.45
     Other
    2.42
    のお話
    2.38
     összefoglaló
    2.36
    蠓
    2.31
    铙
    2.31
    Activations Density 0.006%

    No Known Activations