© 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. 31340
    Prev
    Next
    INDEX
    Explanations

    here's a

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

    cement tile

    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
    腾
    0.48
    陲
    0.47
    承担
    0.46
    置
    0.46
     পুল
    0.44
    围绕
    0.44
    显示
    0.43
    外科
    0.43
    原则
    0.43
    坻
    0.42
    POSITIVE LOGITS
     spices
    0.57
    spice
    0.55
     renseignements
    0.52
     spice
    0.51
     metagen
    0.51
     suboptimal
    0.50
     software
    0.50
     ransomware
    0.50
     genotypes
    0.49
    ing
    0.48
    Activations Density 0.000%

    No Known Activations