© 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. 135742
    Prev
    Next
    INDEX
    Explanations

    President Mubarak

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

    stake, Channels, Clause, missiles, depending, function, free, cartoon

    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
    䣨
    0.49
    வர்களாக
    0.49
    processor
    0.48
    ="",
    0.48
    一个月
    0.47
     नयी
    0.47
    ድረግ
    0.46
    ዘጋ
    0.46
    חות
    0.45
    audience
    0.45
    POSITIVE LOGITS
    '
    0.55
    ’
    0.53
     B
    0.51
     cot
    0.50
     BIB
    0.46
    ®
    0.46
     Bur
    0.45
     seafront
    0.45
     disturbs
    0.45
     stained
    0.44
    Activations Density 0.000%

    No Known Activations