© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 70126
    Prev
    Next
    INDEX
    Explanations

    close to home

    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
     DESCRIPT
    -0.77
     الشاشة
    -0.77
    الس
    -0.74
     COMMAND
    -0.74
     Transvaal
    -0.71
    ර
    -0.71
    meen
    -0.71
    recipe
    -0.71
    agus
    -0.70
     agr
    -0.70
    POSITIVE LOGITS
     closer
    1.22
     home
    1.21
     hits
    1.16
    Closer
    1.13
    hits
    1.03
     hit
    1.03
     Closer
    1.03
     close
    1.02
     Hits
    0.99
    CLOSE
    0.91
    Activations Density 0.016%

    No Known Activations