© 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. 79271
    Prev
    Next
    INDEX
    Explanations

    decision, epidemics, waiter, expectations, activities

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

    abstract ideas and actions

    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
    <b>
    0.59
    snap
    0.45
    '.
    0.44
     or
    0.44
    experience
    0.43
     যেটি
    0.43
    <u>
    0.41
     যেগুলো
    0.41
    vagrant
    0.41
    <strong>
    0.40
    POSITIVE LOGITS
     কণ্ঠে
    0.45
     weiterhin
    0.44
     diminue
    0.44
    dorff
    0.43
     ayudarte
    0.42
     sağlıklı
    0.42
    ോടെ
    0.41
    Milliseconds
    0.41
     wyłącznie
    0.41
    ানিতে
    0.41
    Activations Density 0.000%

    No Known Activations