© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 106864
    Prev
    Next
    INDEX
    Explanations

    place of dwelling

    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
     додат
    -0.69
     ASPECTS
    -0.68
     conductance
    -0.67
     assume
    -0.67
    ही
    -0.66
    냅
    -0.66
     Sortiment
    -0.66
    eien
    -0.65
    デッキ
    -0.65
     assuming
    -0.65
    POSITIVE LOGITS
     abode
    3.19
     dwelling
    2.69
     residence
    2.50
     habitat
    2.03
     dwellings
    1.89
     Abo
    1.89
    dwelling
    1.85
     morada
    1.83
    residence
    1.83
     home
    1.80
    Activations Density 0.043%

    No Known Activations