© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 89200
    Prev
    Next
    INDEX
    Explanations

    receive, acquire, accommodating

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

    country codes and multi-word phrases

    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
    နေရာ
    0.52
     Zit
    0.48
     bề
    0.47
    ಷ್ಟ
    0.47
     Thous
    0.46
     sirop
    0.45
     inz
    0.45
    짬
    0.45
     vanished
    0.44
    懒
    0.44
    POSITIVE LOGITS
    ting
    0.42
    temporary
    0.40
    marine
    0.39
    lje
    0.39
    tingham
    0.39
     postponing
    0.38
     ثالث
    0.37
    legate
    0.37
     postpon
    0.37
     особое
    0.36
    Activations Density 0.000%

    No Known Activations