© 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. 15180
    Prev
    Next
    INDEX
    Explanations

    signaling, everyone, could, can, integrating

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

    specific situations and details

    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
     بھی
    0.50
     _____
    0.45
     _______
    0.44
     :,
    0.42
    !!!!!
    0.42
     _____________
    0.42
     también
    0.42
    :<
    0.42
    acay
    0.41
    !!!!!!
    0.41
    POSITIVE LOGITS
    深化
    0.47
    佢
    0.41
    setBounds
    0.40
    פּ
    0.40
    尤其
    0.40
     καρ
    0.39
     पदार्थों
    0.39
    ημ
    0.39
     akin
    0.38
    חת
    0.38
    Activations Density 0.000%

    No Known Activations