© 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. 169030
    Prev
    Next
    INDEX
    Explanations

    arrests, disappointment, abandoned

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

    sources Rootsometimes simplydistant soundsthen aresearching companiesnobody has

    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
     শহরের
    0.52
     ምግብ
    0.48
     কেন
    0.47
    груп
    0.46
    🍟
    0.46
    쁨
    0.45
    㴌
    0.45
     ይቀ
    0.44
    кими
    0.44
     другими
    0.44
    POSITIVE LOGITS
     torsion
    0.48
     artillery
    0.45
     haste
    0.45
     neoplas
    0.45
     marines
    0.44
     Entonces
    0.44
     Artillery
    0.43
     
    0.43
     verdes
    0.42
     Mo
    0.42
    Activations Density 0.000%

    No Known Activations