© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205001
    Prev
    Next
    INDEX
    Explanations

    Android client, children together, the locks

    np_acts-logits-general · gemini-2.5-flash-lite

    API, SMS, text, clinical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Send
    0.51
    /
    0.50
    $/
    0.48
    ،
    0.47
     (
    0.46
    Internet
    0.46
    elephant
    0.46
    ស្
    0.46
     ETF
    0.45
     +
    0.45
    POSITIVE LOGITS
     destinée
    0.47
    ्य
    0.45
    ρη
    0.45
    λιο
    0.45
    িয়াম
    0.45
     pouvoir
    0.44
    არა
    0.44
     esth
    0.44
    رج
    0.43
     Pologne
    0.43
    Activations Density 0.000%

    No Known Activations