© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 34202
    Prev
    Next
    INDEX
    Explanations

    the only, the nature, the latest, the most

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

    the + definitive descriptor

    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
     this
    0.46
     CAA
    0.45
     most
    0.43
     correspond
    0.43
     here
    0.42
     .
    0.41
     này
    0.41
     true
    0.41
     on
    0.40
     ama
    0.40
    POSITIVE LOGITS
    igenschaft
    0.43
    äksi
    0.41
     비슷한
    0.41
     삶
    0.40
    versammlung
    0.40
    expl
    0.40
    ตร์
    0.40
    raisal
    0.40
     사용하는
    0.40
    otrich
    0.39
    Activations Density 0.067%

    No Known Activations