© 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. 59811
    Prev
    Next
    INDEX
    Explanations

    abandoned, rejection, forsaken, neglected

    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
    はなく
    -1.39
     to
    -1.39
     =
    -1.34
    下列
    -1.34
    Still
    -1.31
     idolat
    -1.28
    lient
    -1.26
     Mts
    -1.26
     siguientes
    -1.26
    <em>
    -1.25
    POSITIVE LOGITS
    
    1.60
    夘
    1.43
    Deportes
    1.43
     regels
    1.42
     tussen
    1.41
    Cuad
    1.41
    acağ
    1.38
    IRIT
    1.38
    亟
    1.36
    breviations
    1.35
    Activations Density 0.023%

    No Known Activations