© 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. 69662
    Prev
    Next
    INDEX
    Explanations

    travel or visits

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

    buy low sell high

    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
    recur
    0.50
    uncie
    0.49
     baca
    0.48
    uki
    0.46
    uku
    0.46
     $(<
    0.46
    <unused652>
    0.45
    곸
    0.44
    ũng
    0.44
    ulie
    0.44
    POSITIVE LOGITS
     Leaves
    0.43
     året
    0.42
     zonder
    0.41
     reactionary
    0.41
    押
    0.41
     ক্লাশ
    0.41
     वेव्स
    0.40
     yılları
    0.40
    Leaves
    0.40
    রাষ্ট্রম
    0.39
    Activations Density 0.000%

    No Known Activations