© 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. 103339
    Prev
    Next
    INDEX
    Explanations

    android id attributes

    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
    ఝ
    -0.89
    ала
    -0.87
    рослав
    -0.84
    familie
    -0.82
     surpren
    -0.81
     帅
    -0.81
    дю
    -0.81
     funktioner
    -0.81
     gangen
    -0.81
    CHIN
    -0.81
    POSITIVE LOGITS
    iv
    1.01
     similar
    0.87
    ll
    0.87
    ff
    0.85
     each
    0.82
    rl
    0.82
     at
    0.82
     none
    0.81
    id
    0.80
    ata
    0.80
    Activations Density 0.001%

    No Known Activations