© 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. 34-GEMMASCOPE-RES-131K
    7. 1686
    Prev
    Next
    INDEX
    Explanations

    my place or someone's house

    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_34/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
    ⎣
    -0.88
     gradual
    -0.86
     begun
    -0.85
     zwölf
    -0.85
     palav
    -0.82
    頬
    -0.81
     entire
    -0.81
     beispielsweise
    -0.78
    eed
    -0.78
     inside
    -0.78
    POSITIVE LOGITS
     house
    2.45
     place
    2.20
     houses
    1.56
     domu
    1.39
    บ้าน
    1.30
    place
    1.28
     apartment
    1.27
     office
    1.24
    Place
    1.19
    thouse
    1.13
    Activations Density 0.031%

    No Known Activations