© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60581
    Prev
    Next
    INDEX
    Explanations

    firmware and UEFI

    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
    ㉗
    -2.88
    缡
    -2.83
     («
    -2.64
    ꜆
    -2.61
    或
    -2.58
    鶫
    -2.55
    تیجه
    -2.50
    ’
    -2.44
     dà
    -2.42
    ᅫ
    -2.38
    POSITIVE LOGITS
    .
    3.19
     …”
    2.56
    鱘
    2.47
    I
    2.28
                
    2.27
     для
    2.25
    噚
    2.19
    媄
    2.16
    
    2.16
     intentó
    2.16
    Activations Density 0.001%

    No Known Activations