© 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. 49552
    Prev
    Next
    INDEX
    Explanations

    China, Information Technology

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

    miner extractible value, trust atoms

    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
     toer
    0.42
     TreeSet
    0.41
     compulsion
    0.41
     žmon
    0.41
     benchmarks
    0.40
     immutable
    0.40
     upheaval
    0.40
    𝒞
    0.39
    uttab
    0.38
    
    0.38
    POSITIVE LOGITS
    掌握
    0.41
    各自
    0.41
     Artist
    0.40
    大战
    0.40
    意見
    0.39
    եր
    0.39
    नर
    0.38
     действу
    0.38
    ភាគ
    0.38
     كلهم
    0.38
    Activations Density 0.069%

    No Known Activations