© 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. 103347
    Prev
    Next
    INDEX
    Explanations

    names starting with Alberto

    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
    y
    -3.00
    x
    -2.89
     blissful
    -2.67
     predominant
    -2.61
     reputable
    -2.58
    方法
    -2.53
    An
    -2.52
     impressive
    -2.47
    It
    -2.44
     weirdly
    -2.39
    POSITIVE LOGITS
    اً
    2.72
    骜
    2.67
    ly
    2.61
    
    2.48
    猡
    2.45
    栳
    2.44
    itiert
    2.39
     花纹
    2.38
    薜
    2.38
    
    2.36
    Activations Density 0.004%

    No Known Activations