© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13453
    Prev
    Next
    INDEX
    Explanations

    Ballitore, exterior, sell

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

    happens through

    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_16k_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
     prohibitive
    0.54
    Aslamualaikum
    0.53
     Djokovic
    0.52
     inconvenient
    0.48
    港
    0.48
    張
    0.47
    震撼
    0.47
    巾
    0.47
    中有
    0.46
    控制器
    0.46
    POSITIVE LOGITS
    Vx
    0.46
     />
    0.44
    OnOff
    0.43
    Um
    0.43
     contribute
    0.42
    Stu
    0.42
     createjs
    0.41
    ondata
    0.41
     getMenuInflater
    0.41
    sofar
    0.41
    Activations Density 0.000%

    No Known Activations