© 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. 22192
    Prev
    Next
    INDEX
    Explanations

    sorting by popularity, rating, or price

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

    sorting and ranking by popularity or price

    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
     اهل
    0.43
    ü
    0.43
     Cities
    0.41
    Brief
    0.41
    ůj
    0.41
     Citi
    0.40
     都市
    0.40
     प्रतिनिधियों
    0.40
    謃
    0.40
    igne
    0.40
    POSITIVE LOGITS
     vectorized
    0.48
     tumult
    0.46
     hypothesis
    0.46
    排序
    0.45
     meniscus
    0.45
     glitch
    0.43
     coin
    0.42
     thiol
    0.41
     moon
    0.41
     fragrance
    0.41
    Activations Density 0.000%

    No Known Activations